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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241521
    Prev
    Next
    INDEX
    Explanations

    file permissions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_262k_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
     Nucleaire
    0.60
     grapple
    0.56
    <0xBC>
    0.55
    aryng
    0.55
    轻易
    0.55
    empat
    0.55
    зя
    0.54
    زيد
    0.54
     valid
    0.53
     defocus
    0.53
    POSITIVE LOGITS
    margin
    0.59
    複合
    0.56
     существу
    0.54
    夢
    0.54
     താ
    0.53
    fileobj
    0.53
    幌
    0.52
     margin
    0.52
    ல்கள்
    0.52
     проводи
    0.51
    Activations Density 0.001%

    No Known Activations