© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1990
    Prev
    Next
    INDEX
    Explanations

    US states and Canadian provinces

    np_acts-logits-general · gemini-2.5-flash-lite

    states in United States

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    Afghan
    0.45
    ឡិចត្រូ
    0.42
     Parisian
    0.40
    札幌
    0.40
    傣
    0.40
     ITER
    0.40
     అలీ
    0.38
    
    0.38
    countries
    0.38
     mannit
    0.38
    POSITIVE LOGITS
     Illinois
    0.92
     Pennsylvania
    0.87
     Massachusetts
    0.87
     штат
    0.85
     Missouri
    0.84
     Ohio
    0.80
     Minnesota
    0.79
     Calif
    0.78
     Ontario
    0.78
     Alabama
    0.78
    Activations Density 0.315%

    No Known Activations