© 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. 158876
    Prev
    Next
    INDEX
    Explanations

    designation, letter, detail, organize, deaths, casino

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

    environments

    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
    他們的
    0.57
     آنها
    0.53
     Eigenschaften
    0.52
     Beispiele
    0.50
     Архи
    0.50
     illetve
    0.50
     alebo
    0.49
     热
    0.49
     Pflicht
    0.49
     Ло
    0.48
    POSITIVE LOGITS
    tono
    0.50
    ラクマ
    0.48
    module
    0.48
    interaction
    0.48
    twilio
    0.46
    OR
    0.46
    tube
    0.46
    tab
    0.45
    newcommand
    0.45
     sunroof
    0.45
    Activations Density 0.000%

    No Known Activations