© 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. 9568
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis or semicolon

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

    This neuron responds to tokens that contain digits—e.g. numeric identifiers in code labels, line‐number variables, citation numbers, or other digit‐heavy tokens.

    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
     lockdowns
    0.58
     covid
    0.57
     morales
    0.56
     tqdm
    0.55
     GWAS
    0.55
     書き
    0.55
     policing
    0.54
     ㅛ
    0.54
     inscreva
    0.53
     havoc
    0.52
    POSITIVE LOGITS
    If
    0.99
    if
    0.99
    ถ้า
    0.96
     if
    0.92
    如果没有
    0.91
    Если
    0.90
    Nếu
    0.87
    если
    0.85
     যদি
    0.84
    如果
    0.83
    Activations Density 0.000%

    No Known Activations