© 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. 17586
    Prev
    Next
    INDEX
    Explanations

    regions followed by province

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

    geographical provinces

    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
    骶
    0.43
     perpendicular
    0.41
     মার্ট
    0.40
     جور
    0.37
     Sonic
    0.37
    壘
    0.37
     Deadline
    0.36
     FGFR
    0.36
    얏
    0.36
     leisure
    0.36
    POSITIVE LOGITS
     province
    4.25
     Province
    4.13
    省
    4.13
    province
    4.03
    Province
    3.91
     provincial
    3.88
     провин
    3.83
     provinces
    3.78
     provincia
    3.78
     provinc
    3.67
    Activations Density 0.085%

    No Known Activations