© 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. 7882
    Prev
    Next
    INDEX
    Explanations

    national and global scope

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

    worldwide scope

    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
    imori
    0.36
     Hagan
    0.35
     ConcurrentTask
    0.35
    ᒎ
    0.34
     دریا
    0.34
     ಯಾವುದ
    0.33
    ኋ
    0.33
     Whatever
    0.33
    ੲ
    0.33
     একখানি
    0.32
    POSITIVE LOGITS
    ทั่ว
    3.34
     worldwide
    3.25
    worldwide
    3.03
     nationwide
    3.00
    全国
    2.72
     Worldwide
    2.67
     khắp
    2.67
    Worldwide
    2.66
     전국
    2.58
     weltweit
    2.53
    Activations Density 0.488%

    No Known Activations