© 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. 102401
    Prev
    Next
    INDEX
    Explanations

    Frame Structure

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

    i'm on energy-saving mode

    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
    ଃ
    0.50
    durch
    0.49
    スタンダ
    0.46
    マネ
    0.44
    skoj
    0.44
     znaleźć
    0.44
     znajdu
    0.43
    スタンド
    0.43
    スポット
    0.42
    トラン
    0.42
    POSITIVE LOGITS
    ->
    0.50
    à
    0.49
     미리
    0.47
     get
    0.47
     à
    0.46
    维护
    0.46
    డో
    0.43
    输出
    0.43
    ay
    0.43
    ifier
    0.42
    Activations Density 0.000%

    No Known Activations