© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 508
    Prev
    Next
    INDEX
    Explanations

    Enrique or hippocampal

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

    first names or personal identifiers, particularly at the beginning of biographical information.

    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
    ”,
    -3.20
    on
    -3.19
    It
    -3.13
    ’,
    -3.00
    ta
    -2.95
    In
    -2.94
    -
    -2.83
    ”:
    -2.77
    m
    -2.75
    is
    -2.73
    POSITIVE LOGITS
    
    2.97
    
    2.92
     achet
    2.91
     desapar
    2.81
    鬭
    2.78
    蟊
    2.72
    纐
    2.72
    唧
    2.67
    隳
    2.67
    鱨
    2.66
    Activations Density 0.004%

    No Known Activations