© 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. 58272
    Prev
    Next
    INDEX
    Explanations

    Messiah, Christ, Hendrix, MHC

    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
     gewähr
    -2.69
    ője
    -2.23
     ersche
    -2.22
    와
    -2.17
     comienzos
    -2.17
    8
    -2.11
     ApiClient
    -2.05
     vermag
    -2.03
    0
    -2.03
     accompanying
    -2.00
    POSITIVE LOGITS
    {
    2.53
     I
    2.33
    s
    2.09
     they
    2.05
    ↵
    1.96
    </b>
    1.94
    йки
    1.83
     During
    1.83
    ↵↵
    1.81
     him
    1.78
    Activations Density 0.003%

    No Known Activations