© 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. 55347
    Prev
    Next
    INDEX
    Explanations

    Scandinavian Society

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

    setting or describing states

    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
    চ
    0.53
    ली
    0.53
    ,
    0.50
    MON
    0.48
    лость
    0.48
    ედ
    0.47
    ൽ
    0.45
    λα
    0.44
    מי
    0.43
    ेड
    0.43
    POSITIVE LOGITS
    fig
    0.54
    ujete
    0.53
     எடுத்துக்
    0.49
     Fig
    0.45
    opies
    0.45
     மாசுபடுத்த
    0.44
     приложение
    0.43
    .).
    0.43
    ienen
    0.43
     நுரையீரல்
    0.43
    Activations Density 0.000%

    No Known Activations