© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15508
    Prev
    Next
    INDEX
    Explanations

    SMART Program, Mailer, tabBar, tomography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    嫑
    -2.97
     ส์
    -2.84
    ⑊
    -2.81
    廰
    -2.70
    genodigd
    -2.67
    樒
    -2.66
    blech
    -2.66
    囖
    -2.63
    秫
    -2.59
    饪
    -2.58
    POSITIVE LOGITS
     but
    2.84
    as
    2.81
     .
    2.56
    you
    2.53
    (
    2.34
    \
    2.34
     After
    2.31
     
    2.20
     so
    2.08
     it
    2.00
    Activations Density 0.005%

    No Known Activations