© 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. 38414
    Prev
    Next
    INDEX
    Explanations

    Southampton Football Club

    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
    Negative Logits
     kurzem
    -2.61
     bedienen
    -2.53
     verlangen
    -2.36
    同じ
    -2.28
    有
    -2.27
    vités
    -2.20
     卒業
    -2.19
     如果
    -2.17
     nếu
    -2.17
     You
    -2.17
    POSITIVE LOGITS
     zusätzlich
    2.20
     fateful
    2.19
     That
    2.14
     It
    2.13
    囪
    2.03
    ????????
    1.96
     ventured
    1.95
     weken
    1.92
     وأن
    1.91
    “
    1.91
    Activations Density 0.001%

    No Known Activations