© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15039
    Prev
    Next
    INDEX
    Explanations

    Connecticut

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
    🏜
    0.71
     Egyptian
    0.70
     Egypt
    0.70
     egyptian
    0.70
    Egypt
    0.68
    Egyptian
    0.68
     vapour
    0.67
    🌵
    0.67
     Nile
    0.66
     ruby
    0.64
    POSITIVE LOGITS
     Connecticut
    3.23
    Connecticut
    3.16
     UConn
    2.95
     Hartford
    2.52
     CT
    2.42
     Stamford
    2.09
     Bridgeport
    2.09
    CT
    1.96
     Norwalk
    1.91
    Yale
    1.90
    Activations Density 0.102%

    No Known Activations