© 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. 34-GEMMASCOPE-RES-131K
    7. 63849
    Prev
    Next
    INDEX
    Explanations

    nurse roles and professions

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

    This neuron activates for mentions of nurses, nursing, and nurse practitioners in healthcare contexts.

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

    This neuron detects occurrences of the word “nurse” (in any form or compound, e.g. nurse, nurses, nurse practitioners, nurse managers, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Massive
    -0.92
     Juifs
    -0.90
     sickly
    -0.85
    شان
    -0.84
    Configura
    -0.81
     Lists
    -0.81
    麼
    -0.81
    蒐
    -0.81
     stipulations
    -0.80
     pensato
    -0.80
    POSITIVE LOGITS
    maid
    1.41
     practitioner
    1.22
    煨
    0.97
    joy
    0.95
    bys
    0.95
    ingale
    0.94
    maids
    0.93
     manager
    0.93
    ZA
    0.92
     Practitioner
    0.91
    Activations Density 0.007%

    No Known Activations