© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 36259
    Prev
    Next
    INDEX
    Explanations

    python __init__ method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
    時計
    0.46
    ʡ
    0.44
    }:$
    0.43
     verwenden
    0.43
     funkci
    0.43
     除了
    0.43
    FunctionName
    0.43
    왈
    0.42
    が出
    0.42
     フル
    0.41
    POSITIVE LOGITS
     Tổ
    0.45
    nd
    0.45
     holdings
    0.44
     Humanities
    0.43
     moi
    0.41
     Paintings
    0.40
    ű
    0.40
     Recursos
    0.40
     Holdings
    0.39
    maar
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.