© 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. 12577
    Prev
    Next
    INDEX
    Explanations

    0 followed by 6

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

    The neuron is highly sensitive to numeric tokens (digits, numbers, and numerical values).

    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
    س
    0.77
    تها
    0.73
    ش
    0.72
    ला
    0.71
    я
    0.70
    ीकृत
    0.69
    िलो
    0.68
    لها
    0.68
    鱈
    0.68
    し
    0.66
    POSITIVE LOGITS
     Commandments
    0.86
     กว่า
    0.79
     commandments
    0.78
     bữa
    0.69
     lét
    0.68
    ވާ
    0.68
     Chancery
    0.67
    ^{-
    0.67
     HUOBI
    0.66
     벌
    0.65
    Activations Density 0.213%

    No Known Activations