© 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. 58223
    Prev
    Next
    INDEX
    Explanations

    nation

    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
    Negative Logits
    亖
    -2.02
    鳧
    -1.95
     Namun
    -1.88
    </strong>
    -1.83
    …"
    -1.77
     Одна
    -1.76
    鈇
    -1.74
    蹋
    -1.73
     صفحۀ
    -1.72
    🢒
    -1.72
    POSITIVE LOGITS
    </b>
    2.22
    (
    2.05
     &
    1.98
    ꦭ
    1.95
    %
    1.91
     impone
    1.83
    </h5>
    1.80
    m
    1.78
    ва
    1.77
    着脸
    1.77
    Activations Density 0.005%

    No Known Activations