© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 174004
    Prev
    Next
    INDEX
    Explanations

    time ago

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

    breaking down listed information

    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
    ور
    0.48
     warden
    0.44
    /
    0.44
     Ur
    0.43
    య
    0.43
    urada
    0.42
     Shahid
    0.42
     commandant
    0.42
     Nem
    0.41
    യെ
    0.41
    POSITIVE LOGITS
    <unused674>
    0.48
    ⇅
    0.46
    Stamped
    0.46
    Celebrate
    0.46
    GetService
    0.45
    LER
    0.45
    ToExp
    0.45
    ρια
    0.45
     ইন্টারনেট
    0.45
    踉
    0.45
    Activations Density 0.001%

    No Known Activations