© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3590
    Prev
    Next
    INDEX
    Explanations

    participating in or improving something

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

    The neuron flags high-information content words—especially substantive nouns and verbs—rather than common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     и
    1.08
    และ
    1.03
     અને
    1.02
     và
    1.00
     and
    0.96
     και
    0.95
     और
    0.95
     এবং
    0.94
     және
    0.89
     و
    0.88
    POSITIVE LOGITS
     sebagainya
    0.86
     நிச்சயமாக
    0.71
     diğer
    0.65
     lainnya
    0.61
     heartbreak
    0.61
     送料無料
    0.60
     බොහෝ
    0.60
     tentunya
    0.59
    句話
    0.59
     ໃນ
    0.58
    Activations Density 0.001%

    No Known Activations