© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 20719
    Prev
    Next
    INDEX
    Explanations

    linked or correlated over distance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     شرطونه
    0.47
     Π
    0.47
     యా
    0.46
     факторы
    0.45
     фонбет
    0.44
     patitth
    0.44
     και
    0.44
     المح
    0.44
     upland
    0.43
     بذلك
    0.43
    POSITIVE LOGITS
    us
    0.52
     consum
    0.52
    ist
    0.51
     orchestration
    0.48
    being
    0.48
    時
    0.48
    šti
    0.48
    rus
    0.47
    to
    0.46
    week
    0.45
    Activations Density 0.002%

    No Known Activations