© 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. 7030
    Prev
    Next
    INDEX
    Explanations

    css dimensions and percentages

    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
    辚
    -3.02
    琲
    -2.95
     permettant
    -2.86
    鶿
    -2.77
     deliciously
    -2.75
    神情
    -2.72
     เรา
    -2.69
     свою
    -2.61
    
    -2.61
    他們
    -2.56
    POSITIVE LOGITS
     if
    3.13
     for
    2.77
    ).
    2.70
    家居
    2.69
     in
    2.58
     because
    2.48
     at
    2.45
     as
    2.41
     on
    2.36
    家用
    2.31
    Activations Density 0.005%

    No Known Activations