© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 291
    Prev
    Next
    INDEX
    Explanations

    Vancouver and British Columbia locations

    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
     Ontario
    -0.99
    TokenName
    -0.90
    🇱
    -0.89
     Toronto
    -0.88
     Omaha
    -0.88
     Nebraska
    -0.84
    tanggal
    -0.84
     Huron
    -0.82
     derecho
    -0.82
    Nebraska
    -0.82
    POSITIVE LOGITS
     Vancouver
    2.30
    Vancouver
    2.17
     BC
    1.95
    BC
    1.82
     UBC
    1.50
     Okan
    1.42
    British
    1.41
     Colombie
    1.38
    Seattle
    1.38
    Pacific
    1.38
    Activations Density 0.095%

    No Known Activations