© 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. 58282
    Prev
    Next
    INDEX
    Explanations

    politicians and government issues

    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
     at
    -1.48
     digunakan
    -1.48
    Več
    -1.47
     in
    -1.35
    盦
    -1.32
     nadzie
    -1.31
     around
    -1.30
     mereka
    -1.29
     from
    -1.27
     for
    -1.26
    POSITIVE LOGITS
    んでる
    1.59
     تنها
    1.53
     what
    1.48
     now
    1.43
    现在的
    1.34
     who
    1.33
     {//
    1.31
    ;//
    1.31
    客様
    1.30
     !(
    1.27
    Activations Density 0.171%

    No Known Activations