© 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. 22626
    Prev
    Next
    INDEX
    Explanations

    surface area

    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
    (
    -1.98
     bendera
    -1.70
    
    -1.70
    {
    -1.66
     rostros
    -1.66
    ⸨
    -1.64
    $("
    -1.60
     maaf
    -1.60
    ){
    -1.59
     sélections
    -1.55
    POSITIVE LOGITS
     of
    1.98
    豺
    1.83
    蟑
    1.69
     bedeutet
    1.68
     automate
    1.67
    睪
    1.63
    おきます
    1.63
     assure
    1.62
    IconModule
    1.62
     והוא
    1.61
    Activations Density 0.005%

    No Known Activations