© 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-65K
    7. 15017
    Prev
    Next
    INDEX
    Explanations

    typical

    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_65k_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
     Gubern
    0.60
    mapbox
    0.57
     Zas
    0.56
    References
    0.54
     References
    0.54
     ।*
    0.53
     TRAN
    0.52
    Bankruptcy
    0.52
    켤
    0.52
     Doesn
    0.51
    POSITIVE LOGITS
     typical
    0.82
    Typical
    0.79
     Typical
    0.76
    Estimated
    0.76
    typical
    0.74
     типи
    0.71
    Predicted
    0.66
     Estimated
    0.66
     típico
    0.65
    Accessor
    0.64
    Activations Density 0.004%

    No Known Activations