© 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. 168468
    Prev
    Next
    INDEX
    Explanations

    astrology and places

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

    MACD Line, Theme Days, Survival Day

    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
    Ր
    0.46
     اتار
    0.46
    工作人员
    0.46
    ንሽ
    0.46
     الواحد
    0.45
    يرات
    0.45
     hátsó
    0.45
    喑
    0.45
     單
    0.44
    resses
    0.44
    POSITIVE LOGITS
     Gwyn
    0.51
    source
    0.47
     digestibility
    0.47
     недостаточно
    0.47
     Vincenzo
    0.47
     source
    0.47
     запись
    0.46
     pły
    0.46
     >>=
    0.46
     сле
    0.46
    Activations Density 0.000%

    No Known Activations