© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4261
    Prev
    Next
    INDEX
    Explanations

    specific subjects

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

    The neuron strongly activates on substantive content words (significant nouns, verbs, or adjectives) rather than on function words or punctuation.

    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
    -
    0.61
    ový
    0.61
     anden
    0.56
     preprint
    0.55
     hemorrhage
    0.55
     constructed
    0.55
    2
    0.55
     emphasizing
    0.55
     niya
    0.55
     rumored
    0.55
    POSITIVE LOGITS
    mselves
    0.75
    ፣
    0.69
     डिफरेंट
    0.63
     nuances
    0.63
    样子
    0.61
    𝙏
    0.61
    necessary
    0.60
     Unterschiede
    0.60
    لیکن
    0.60
    возмо
    0.59
    Activations Density 0.648%

    No Known Activations