© 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. 34-GEMMASCOPE-RES-131K
    7. 79493
    Prev
    Next
    INDEX
    Explanations

    border width or pixel value

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     avenger
    -0.87
    luent
    -0.76
     årene
    -0.75
     fince
    -0.74
    hiba
    -0.73
    Duane
    -0.71
     TSC
    -0.71
     parabola
    -0.71
     ravages
    -0.70
     lorem
    -0.70
    POSITIVE LOGITS
     hair
    1.47
     StyleSheet
    1.29
     ONE
    1.00
     pixel
    0.98
     pennies
    0.98
     Hair
    0.96
    hair
    0.95
     penny
    0.94
     one
    0.94
    Hair
    0.90
    Activations Density 0.012%

    No Known Activations