© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 934
    Prev
    Next
    INDEX
    Explanations

    canada and canadian cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    溧
    1.06
     Arroyo
    1.05
    ادہ
    1.05
    
    1.03
     Liet
    1.02
    ăș
    1.00
     Rubio
    0.98
     አል
    0.97
     슈
    0.95
    彝
    0.93
    POSITIVE LOGITS
     Canadians
    3.14
     Canada
    3.13
     Canadian
    3.11
     Ontario
    3.06
    Canada
    3.06
     Manitoba
    2.98
     Ottawa
    2.95
     Quebec
    2.95
    Ontario
    2.94
    Canadian
    2.93
    Activations Density 1.657%

    No Known Activations