© 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. 172193
    Prev
    Next
    INDEX
    Explanations

    why? estimate the. was added. who. Step. toe. think

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

    Among Us

    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
     P
    0.48
    TH
    0.47
     guards
    0.46
    を起こ
    0.46
     (
    0.45
    P
    0.45
    Time
    0.44
     buckling
    0.44
    Not
    0.43
    ئے
    0.42
    POSITIVE LOGITS
    يب
    0.56
    ाइट
    0.50
    욌
    0.49
    opez
    0.49
    elab
    0.49
     색
    0.48
    색
    0.48
     콘텐츠
    0.48
    㠃
    0.47
    🤩
    0.47
    Activations Density 0.000%

    No Known Activations