© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66907
    Prev
    Next
    INDEX
    Explanations

    medical care contexts

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

    healthcare and nursing-related terminology, including clinical practices, patient care, medical procedures, and nursing education.

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

    This neuron detects specialized terminology from academic nursing articles, especially phrases about medication administration, clinical practice, and student nurse preparedness.

    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
     to
    -2.16
    ≙
    -1.61
     mengumumkan
    -1.55
     sains
    -1.46
     pering
    -1.42
     staten
    -1.41
    Provincia
    -1.35
     marta
    -1.35
     کردی
    -1.34
     comparaison
    -1.31
    POSITIVE LOGITS
     during
    1.91
     before
    1.88
     with
    1.72
     at
    1.69
     χρησιμοποι
    1.53
    ก่อน
    1.52
     first
    1.49
    女人
    1.45
     while
    1.45
    readFileSync
    1.45
    Activations Density 0.335%

    No Known Activations