© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3199
    Prev
    Next
    INDEX
    Explanations

    excels at / looks at

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

    This neuron fires on dynamic action words—especially verbs that describe doing, trying, or directing something (e.g. “take a crack,” “aimed,” “look,” “try,” “laugh,” “glared,” “cursed”).

    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
    ங்களிலிருந்து
    0.52
    ágico
    0.51
    敕
    0.51
    idual
    0.51
     பற்றிய
    0.51
    郁
    0.51
    ينه
    0.50
    원이
    0.50
     خواہ
    0.50
     तळ
    0.49
    POSITIVE LOGITS
     at
    1.47
    於
    1.38
    于
    1.37
     tại
    1.15
     atthe
    1.09
     于
    0.95
     ở
    0.85
     Tại
    0.81
    Tại
    0.74
     attho
    0.71
    Activations Density 0.257%

    No Known Activations