© 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. 106231
    Prev
    Next
    INDEX
    Explanations

    data repository or workshop links

    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
     Wishlist
    -0.94
     wishlist
    -0.93
     refund
    -0.86
     refunded
    -0.81
    wishlist
    -0.79
     Refund
    -0.77
    Scénario
    -0.74
    Fabric
    -0.74
     reimbursed
    -0.73
    jména
    -0.72
    POSITIVE LOGITS
     workshop
    1.21
     Workshop
    1.19
     workshops
    1.00
    Workshop
    0.91
    workshop
    0.91
    ė
    0.83
     WORKSHOP
    0.83
     Workshops
    0.73
    Workshops
    0.71
     Statistical
    0.70
    Activations Density 0.020%

    No Known Activations