© 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-262K
    7. 123558
    Prev
    Next
    INDEX
    Explanations

    review and context

    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_262k_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
     пределах
    0.47
    肐
    0.46
     모두
    0.46
     효율
    0.46
    트
    0.45
    삭
    0.45
     '.'
    0.44
     영역
    0.44
     заг
    0.44
     apartness
    0.44
    POSITIVE LOGITS
     Hybrid
    0.54
     Rock
    0.46
     hybrid
    0.46
     Street
    0.46
     Highway
    0.45
     Kun
    0.45
     Bell
    0.44
     Lithuanian
    0.44
     ROCK
    0.43
    街
    0.43
    Activations Density 0.002%

    No Known Activations