© 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. 98243
    Prev
    Next
    INDEX
    Explanations

    delivery and years

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

    music will be, with your, legally purchasing

    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
     μόνο
    0.46
    婦
    0.46
    債
    0.46
     housewives
    0.45
     消費
    0.43
     coalgebras
    0.43
     supaya
    0.42
    wives
    0.42
    ,*/}*.
    0.42
     ምግብ
    0.42
    POSITIVE LOGITS
    at
    0.57
    Secondary
    0.51
    ться
    0.51
    от
    0.49
    the
    0.47
    Standard
    0.47
     стандарт
    0.47
    辊
    0.46
    The
    0.45
    Ultimate
    0.45
    Activations Density 0.001%

    No Known Activations