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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1815
    Prev
    Next
    INDEX
    Explanations

    Canada, Canadian

    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_17_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
    1.22
    
    1.15
     슈
    1.12
    鱉
    1.09
     አል
    1.08
     турган
    1.01
    
    1.01
     Arroyo
    1.01
     キー
    1.00
    蓁
    0.99
    POSITIVE LOGITS
     Canada
    3.15
     Canadian
    3.04
     Canadians
    3.04
    Canada
    3.03
     Ontario
    2.93
     Manitoba
    2.90
     Ottawa
    2.90
     Quebec
    2.89
     Alberta
    2.85
     Winnipeg
    2.82
    Activations Density 1.240%

    No Known Activations