© 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. 22718
    Prev
    Next
    INDEX
    Explanations

    Switzerland and Swiss contexts

    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
    {
    -1.34
     We
    -1.33
     Alles
    -1.26
    ار
    -1.23
    د
    -1.21
     Deine
    -1.20
     Viele
    -1.19
     Нам
    -1.19
    ром
    -1.19
    ta
    -1.19
    POSITIVE LOGITS
    acterísticas
    1.48
    だったが
    1.48
     cará
    1.45
    برة
    1.40
     Switzerland
    1.40
    ";
    1.37
     Cancelar
    1.36
    侩
    1.34
     fotografías
    1.33
    }),
    1.32
    Activations Density 0.073%

    No Known Activations