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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10985
    Prev
    Next
    INDEX
    Explanations

    case medical report

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

    references to case reports and similar document types in medical or scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects occurrences of “case report” (and its plural/heading forms) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    classes
    -1.67
     essentielles
    -1.45
     bergen
    -1.44
     verdo
    -1.41
    ten
    -1.38
    maske
    -1.35
     où
    -1.34
    ordnungen
    -1.31
     וס
    -1.30
    линд
    -1.28
    POSITIVE LOGITS
     that
    2.45
     they
    1.75
     also
    1.44
     information
    1.38
    러한
    1.35
     speziellen
    1.34
    ulence
    1.34
     has
    1.32
     presumably
    1.32
    ,’”
    1.30
    Activations Density 0.064%

    No Known Activations