© 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. 118937
    Prev
    Next
    INDEX
    Explanations

    Supercharging

    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
     considerable
    -0.83
    oleum
    -0.77
     GREAT
    -0.75
     utilization
    -0.72
     View
    -0.72
     Printing
    -0.71
    aughter
    -0.71
    isielt
    -0.70
     December
    -0.69
    フィール
    -0.69
    POSITIVE LOGITS
     ipv
    0.91
    IPv
    0.87
     IPv
    0.86
     brev
    0.86
     torchvision
    0.80
     Idy
    0.79
     Hiroshima
    0.79
     RATIO
    0.78
    lac
    0.77
     GOOGLE
    0.77
    Activations Density 0.006%

    No Known Activations