© 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. 38452
    Prev
    Next
    INDEX
    Explanations

    sports coaching staff

    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
     about
    -1.45
    R
    -1.34
    AP
    -1.31
    all
    -1.28
    ('',
    -1.27
     Substituting
    -1.26
    like
    -1.23
    *
    -1.22
     ihrem
    -1.20
    全て
    -1.20
    POSITIVE LOGITS
    חים
    1.30
     esat
    1.21
     nhưng
    1.21
     gevol
    1.21
     Selanjutnya
    1.20
    Chances
    1.18
    開店
    1.17
     Desain
    1.16
     peça
    1.14
    喫茶
    1.14
    Activations Density 0.027%

    No Known Activations