© 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. 79487
    Prev
    Next
    INDEX
    Explanations

    summary judgment

    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
     Тан
    -0.73
    ぐれ
    -0.69
    remes
    -0.69
    Sqlite
    -0.69
    شنگ
    -0.68
     connais
    -0.66
     nemen
    -0.66
    ningen
    -0.65
    ProductID
    -0.65
    osing
    -0.65
    POSITIVE LOGITS
    rectangular
    0.79
     rectangle
    0.76
     rectangular
    0.76
    Accessor
    0.68
    oula
    0.66
    бора
    0.65
    Wow
    0.65
     transmitted
    0.64
     Wow
    0.63
     Patricia
    0.63
    Activations Density 0.092%

    No Known Activations