© 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. 29960
    Prev
    Next
    INDEX
    Explanations

    URLs and query parameters

    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
    illent
    -0.93
    Ingredientes
    -0.72
    Voltar
    -0.71
     Katalog
    -0.70
    Lew
    -0.69
    thoff
    -0.69
     damper
    -0.68
    concatenate
    -0.67
     sabo
    -0.67
     toffee
    -0.66
    POSITIVE LOGITS
     Year
    0.89
     Award
    0.76
    лар
    0.75
    ้าว
    0.75
    ाहरण
    0.74
     plot
    0.72
     Search
    0.72
    stom
    0.71
     pubblica
    0.71
     YEAR
    0.71
    Activations Density 0.006%

    No Known Activations