© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2321
    Prev
    Next
    INDEX
    Explanations

    across everywhere throughout

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on technical or scientific descriptive terms—especially nouns like “activity,” “conditions,” “life,” and similar jargon used in factual or observational passages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    phrases describing environments or situations with a lot of activity, things present, or people gathered.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    descriptions of high intensity or abundance in a scene—busy activity, dense crowds, or extreme environmental conditions.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     siendo
    0.68
     своему
    0.67
     protegido
    0.66
    自身の
    0.64
     unknowingly
    0.63
     svojim
    0.63
     reside
    0.62
     nestled
    0.62
     महज
    0.62
     inadvertently
    0.62
    POSITIVE LOGITS
     everywhere
    1.48
     Everywhere
    1.33
     throughout
    1.23
    Throughout
    1.13
     Throughout
    1.10
     both
    1.02
     khắp
    1.02
     সর্বত্র
    0.99
     überall
    0.98
    both
    0.97
    Activations Density 0.287%

    No Known Activations