© 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. 33749
    Prev
    Next
    INDEX
    Explanations

    statements about conditions or descriptions

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

    calm irritation

    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
    лизация
    0.48
    ческой
    0.46
     escritura
    0.44
    茜
    0.44
     স্থাপিত
    0.41
    ែល
    0.41
    нгтон
    0.41
    ঞ্চ
    0.41
     Trock
    0.41
     \
    0.41
    POSITIVE LOGITS
    rome
    0.55
    อาจ
    0.50
     Hemen
    0.49
     ધર
    0.47
    ン
    0.47
    stv
    0.47
     clumps
    0.47
    სი
    0.47
     eagles
    0.46
     skyscrapers
    0.46
    Activations Density 0.000%

    No Known Activations