© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110553
    Prev
    Next
    INDEX
    Explanations

    Omicron, Oppenheimer, Ounga

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

    The letter "O" at the beginning of element symbols, chemical formulas, or scientific notations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    which
    -3.27
    C
    -3.16
    to
    -3.06
    up
    -3.03
    by
    -3.02
    that
    -2.95
    W
    -2.80
    end
    -2.78
    when
    -2.77
     artistico
    -2.72
    POSITIVE LOGITS
    çok
    2.92
    厹
    2.73
    읖
    2.50
    苙
    2.50
    缡
    2.48
    kaç
    2.47
    iç
    2.45
    
    2.45
    ⁛
    2.42
    ︐
    2.38
    Activations Density 0.015%

    No Known Activations