© 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. 6456
    Prev
    Next
    INDEX
    Explanations

    non-English characters

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

    The neuron specializes in spotting programming‐related tokens—code syntax, comments, decorators, and technical identifiers.

    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
    MOV
    0.55
    ゅう
    0.54
    SG
    0.53
    南京
    0.52
    дви
    0.51
     Bara
    0.50
    꽃
    0.49
    fusc
    0.49
    羊
    0.49
    喃
    0.49
    POSITIVE LOGITS
     azi
    0.56
     कार्
    0.56
     admirer
    0.55
     wal
    0.52
     unver
    0.51
     unfor
    0.50
     admiring
    0.50
     benefitted
    0.49
    ച്ഛ
    0.49
     reporter
    0.49
    Activations Density 0.001%

    No Known Activations