© 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. 62457
    Prev
    Next
    INDEX
    Explanations

    games and sports

    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
    Negative Logits
    ін
    -0.66
     Push
    -0.66
    只会
    -0.64
    態
    -0.64
    canic
    -0.64
     chapitre
    -0.63
    だそうです
    -0.62
    ufel
    -0.62
    emples
    -0.61
    ayak
    -0.61
    POSITIVE LOGITS
    hetamine
    0.69
    Denote
    0.68
     ♪
    0.65
    歙
    0.65
     Greyhound
    0.65
     veg
    0.65
    rouge
    0.65
     Opis
    0.65
    ype
    0.64
     забы
    0.64
    Activations Density 0.058%

    No Known Activations