© 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. 192958
    Prev
    Next
    INDEX
    Explanations

    Ganesha, child, visited

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

    lists, enumerations, and conditions

    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
    Negative Logits
    cieron
    0.50
    vDash
    0.48
     ইনডাক
    0.47
     주변
    0.47
    mprj
    0.46
     ভরে
    0.46
     கொரோனா
    0.46
    缑
    0.46
    コロナ
    0.45
     ソフト
    0.45
    POSITIVE LOGITS
    ardless
    0.46
    рисов
    0.44
    веро
    0.42
     Matters
    0.42
    奸
    0.42
    ர்
    0.41
    ربع
    0.41
    лица
    0.40
    ellation
    0.39
     accolades
    0.39
    Activations Density 0.000%

    No Known Activations