© 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. 16-GEMMASCOPE-2-RES-262K
    7. 120412
    Prev
    Next
    INDEX
    Explanations

    cross-sectional area

    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_16_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
    د
    0.83
    im
    0.70
    丁寧に
    0.66
    ain
    0.65
    ang
    0.64
    ä
    0.63
    ag
    0.62
    ans
    0.62
    angent
    0.61
    ens
    0.60
    POSITIVE LOGITS
    Authorized
    0.64
     مؤرشف
    0.62
    ﺭ
    0.62
    CLASS
    0.61
    Truman
    0.61
    
    0.61
    oooooooo
    0.60
    ။
    0.60
     資料
    0.59
     Polk
    0.59
    Activations Density 0.001%

    No Known Activations