© 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. 222559
    Prev
    Next
    INDEX
    Explanations

    camera, public, account, Library, CMS

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

    planning, recovery, and cleaning processes

    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
    W
    0.56
     мозга
    0.48
    Как
    0.46
     конструкции
    0.46
     победи
    0.45
    SE
    0.45
    KE
    0.45
    JavaScript
    0.45
     модели
    0.44
    AIM
    0.44
    POSITIVE LOGITS
     precedent
    0.47
     बांटा
    0.47
     sentire
    0.46
     xảy
    0.45
    窖
    0.44
     därför
    0.44
    ที่เรา
    0.43
    〗
    0.43
    imageBase
    0.43
    ylen
    0.43
    Activations Density 0.000%

    No Known Activations