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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7966
    Prev
    Next
    INDEX
    Explanations

    if __name__ == "__main__":

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

    This neuron responds to user-interface or engagement action words (e.g. “clicking,” “Post”).

    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_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
     πιο
    0.64
    ddagger
    0.55
    ;++
    0.55
     καλύτε
    0.53
     μέ
    0.53
    vii
    0.52
    -"+
    0.52
     avancé
    0.51
    avaş
    0.51
    startIndex
    0.50
    POSITIVE LOGITS
    หาก
    0.66
     شرح
    0.60
    ར་
    0.58
     Udemy
    0.55
    Ớ
    0.55
     Artwork
    0.54
     ehe
    0.54
     पवित्र
    0.54
     Renov
    0.54
     NodeType
    0.54
    Activations Density 0.000%

    No Known Activations