© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 220297
    Prev
    Next
    INDEX
    Explanations

    finance, bets, pager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    пита
    0.40
     Sutton
    0.39
     piled
    0.39
    endance
    0.38
     nailed
    0.37
     erleben
    0.37
     ட
    0.36
    ट्
    0.36
     पढ़ते
    0.36
    тки
    0.35
    POSITIVE LOGITS
    檚
    0.41
    พ่อ
    0.40
     commutation
    0.39
    選擇
    0.38
    COVID
    0.37
    基地
    0.37
     demora
    0.37
     terrazzo
    0.37
     terraz
    0.36
     commuters
    0.36
    Activations Density 0.005%

    No Known Activations