© 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. 7819
    Prev
    Next
    INDEX
    Explanations

    locality, share, State, foreign, public, enterprise

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

    locality, country, constituent

    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
    โห
    0.48
     lỗi
    0.45
     yên
    0.45
     đc
    0.45
     thoáng
    0.44
    ⛔
    0.44
     Moreover
    0.43
     Toán
    0.43
     الإعلام
    0.43
    🔞
    0.43
    POSITIVE LOGITS
     enterprises
    0.57
     locality
    0.57
     localities
    0.56
     digitalisation
    0.56
     localisation
    0.54
     emphasised
    0.53
     fertiliser
    0.50
    locality
    0.50
     предприятия
    0.50
    localisation
    0.49
    Activations Density 0.018%

    No Known Activations