© 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. 98981
    Prev
    Next
    INDEX
    Explanations

    HTML head sections

    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
    卫生间
    -1.39
     would
    -1.39
     be
    -1.27
     secure
    -1.24
    了不少
    -1.23
     苹果
    -1.23
     技术
    -1.22
     نیروی
    -1.20
    『
    -1.17
    '
    -1.16
    POSITIVE LOGITS
     özellikle
    1.53
    Only
    1.52
    expliquer
    1.45
     with
    1.42
    For
    1.38
    ◾
    1.24
     verändern
    1.24
    with
    1.23
     hjälpa
    1.23
     vklju
    1.22
    Activations Density 0.025%

    No Known Activations