© 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. 76909
    Prev
    Next
    INDEX
    Explanations

    any downloaded

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

    communities and beliefs

    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
    成分
    0.55
    加速
    0.54
    补助
    0.53
    補
    0.52
    燥
    0.52
    补
    0.48
    第二次
    0.47
     زائد
    0.46
    皮肤
    0.46
    烔
    0.46
    POSITIVE LOGITS
    is
    0.63
    iselt
    0.57
    os
    0.52
    opts
    0.52
    number
    0.50
    at
    0.50
    od
    0.48
    ość
    0.48
    isit
    0.48
    le
    0.47
    Activations Density 0.002%

    No Known Activations