© 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. 79268
    Prev
    Next
    INDEX
    Explanations

    vast majority

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Largest
    -1.02
    WRP
    -1.00
     مناط
    -1.00
    眨
    -0.98
     Policía
    -0.96
     теста
    -0.94
    ostatic
    -0.93
    韪
    -0.91
    巴掌
    -0.91
     excludes
    -0.90
    POSITIVE LOGITS
     majority
    1.91
     improvement
    1.20
     array
    1.16
     amount
    1.16
     sprawling
    1.13
     improve
    1.11
    www
    1.11
     improvements
    1.09
     Improve
    1.04
    majority
    1.03
    Activations Density 0.006%

    No Known Activations