© 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. 31759
    Prev
    Next
    INDEX
    Explanations

    activities and email

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

    efficient task completion

    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
     harmless
    0.55
    months
    0.52
     fatally
    0.50
     larceny
    0.50
    ;
    0.50
     legally
    0.49
     fling
    0.49
     pernicious
    0.48
     homicide
    0.47
     hiss
    0.47
    POSITIVE LOGITS
    渔
    0.50
     Typography
    0.48
    报错
    0.47
    还要
    0.47
     Appet
    0.47
    🌭
    0.46
    وهات
    0.46
     нашего
    0.46
     মাছ
    0.45
     আলোকিত
    0.45
    Activations Density 0.000%

    No Known Activations