© 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. 6988
    Prev
    Next
    INDEX
    Explanations

    HTML table attributes

    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
    Some
    -4.13
    When
    -3.98
     When
    -3.84
    There
    -3.83
    Another
    -3.69
    It
    -3.52
    Just
    -3.50
    Using
    -3.47
    Because
    -3.44
    Both
    -3.42
    POSITIVE LOGITS
    宬
    2.94
    ⢅
    2.81
    
    2.80
    
    2.77
    阏
    2.70
    
    2.58
    ⩴
    2.53
    髕
    2.52
    搥
    2.52
     auffi
    2.52
    Activations Density 0.005%

    No Known Activations