© 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. 10-GEMMASCOPE-RES-131K
    7. 12309
    Prev
    Next
    INDEX
    Explanations

    Canadian places and identity

    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
    Not in Any Lists

    No Comments

    Negative Logits
     jednej
    -1.44
    ベ
    -1.34
    García
    -1.34
    sä
    -1.29
    จาก
    -1.29
    ใน
    -1.27
    ดู
    -1.25
    ADOW
    -1.25
    ১
    -1.23
     jedno
    -1.22
    POSITIVE LOGITS
     Canada
    1.56
     Ontario
    1.48
    r
    1.47
     toques
    1.41
     canad
    1.41
     Newfoundland
    1.30
    labour
    1.23
     Canadian
    1.23
     Kanada
    1.22
     odour
    1.20
    Activations Density 0.558%

    No Known Activations