© 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. 72909
    Prev
    Next
    INDEX
    Explanations

    pathogenesis of diseases

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

    the word "pathogenesis" and related terms describing disease development mechanisms.

    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
    </h3>
    -2.17
     the
    -1.81
    身边的
    -1.76
     were
    -1.73
    听见
    -1.63
    regards
    -1.60
    cím
    -1.55
    ⁛
    -1.54
    瞟
    -1.54
     humo
    -1.53
    POSITIVE LOGITS
    ↵
    2.33
     of
    2.08
     leur
    1.80
    1
    1.73
     Here
    1.71
     también
    1.71
    挹
    1.70
    2
    1.67
    1.66
    O
    1.64
    Activations Density 0.086%
    No Known Activations