Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110045
    Prev
    Next
    INDEX
    Explanations

    patient information and appointments

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

    mentions of patient data, records, or medical documentation in technical or healthcare contexts.

    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_34/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
     पू
    -0.73
    сці
    -0.73
    跟着
    -0.72
     Btu
    -0.71
     rebo
    -0.70
     cas
    -0.69
    렇
    -0.69
    цеп
    -0.69
    Ν
    -0.68
    дом
    -0.68
    POSITIVE LOGITS
     appointments
    0.88
     providers
    0.86
    榻
    0.85
    stdarg
    0.80
     resa
    0.80
    Kuva
    0.80
    heri
    0.79
    белый
    0.78
     diven
    0.77
    ativen
    0.76
    Activations Density 0.003%

    No Known Activations