© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60783
    Prev
    Next
    INDEX
    Explanations

    Geneva, Switzerland

    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
    Not in Any Lists

    No Comments

    Negative Logits
     nghi
    -0.73
    нинград
    -0.73
    plusplus
    -0.71
     cabello
    -0.69
     राम
    -0.68
     gekommen
    -0.68
    aguer
    -0.67
     kommen
    -0.66
     hindered
    -0.65
    metrie
    -0.65
    POSITIVE LOGITS
     Geneva
    1.95
    Geneva
    1.66
     CERN
    1.31
     Switzerland
    1.22
    Switzerland
    1.19
     Lausanne
    1.12
     Swiss
    0.97
     Suisse
    0.97
     Rolex
    0.93
     Genève
    0.90
    Activations Density 0.017%

    No Known Activations