© 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. 18296
    Prev
    Next
    INDEX
    Explanations

    comfortableneurontincialisonelaterfaultreservationsdetails

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

    measurement, configuration, or category terms

    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
    超过
    0.34
     অন্যান্য
    0.34
     얼마나
    0.33
    ){
    0.32
     молоко
    0.32
     должно
    0.31
     প্রান্ত
    0.31
    திர
    0.31
     μετα
    0.31
     শিক্ষ
    0.31
    POSITIVE LOGITS
     ieri
    0.32
    ڈر
    0.31
     oni
    0.31
    Then
    0.31
     свої
    0.31
     allerede
    0.30
    ؛
    0.30
     ثم
    0.29
     principale
    0.29
     rossa
    0.29
    Activations Density 0.157%

    No Known Activations