© 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. 41650
    Prev
    Next
    INDEX
    Explanations

    defining terms, specific examples

    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
    esseract
    0.52
     सिद्धांत
    0.51
    ၅
    0.50
    ጴ
    0.50
    apeutics
    0.47
    reporter
    0.46
    istisch
    0.46
     শতাধিক
    0.46
    ôle
    0.46
    ۔۔۔۔
    0.45
    POSITIVE LOGITS
    0.55
     down
    0.49
     TS
    0.49
     TO
    0.48
    I
    0.46
    特定
    0.43
    OU
    0.42
    i
    0.42
     particular
    0.41
     CMS
    0.41
    Activations Density 0.001%

    No Known Activations