© 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. 72366
    Prev
    Next
    INDEX
    Explanations

    titles and names (Saud, Khalifa, II)

    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
     ſou
    -1.65
    比如说
    -1.45
    最后由
    -1.41
    人是
    -1.38
    结语
    -1.37
    做一个
    -1.36
    有趣的
    -1.35
     设计
    -1.31
    再一次
    -1.29
     decisivo
    -1.29
    POSITIVE LOGITS
    ’
    1.80
     also
    1.54
    .
    1.47
    也
    1.23
    弱点
    1.22
    Also
    1.22
    他
    1.21
    ('
    1.20
    同
    1.17
    又
    1.17
    Activations Density 0.003%

    No Known Activations