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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63831
    Prev
    Next
    INDEX
    Explanations

    Ottawa and capital cities

    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
     Johor
    -0.89
     Xperia
    -0.87
    ẫy
    -0.86
     Davao
    -0.83
    berti
    -0.81
     Sharjah
    -0.81
    BRIGHT
    -0.79
     Missoula
    -0.77
    timbangkan
    -0.77
     Panzer
    -0.77
    POSITIVE LOGITS
     Ottawa
    1.88
    Ottawa
    1.52
     Canberra
    1.21
     Carleton
    1.04
     Senators
    0.98
    otta
    0.90
     Barr
    0.89
     Capital
    0.85
    Barr
    0.84
    tawa
    0.84
    Activations Density 0.017%

    No Known Activations