© 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. 34-GEMMASCOPE-RES-131K
    7. 59572
    Prev
    Next
    INDEX
    Explanations

    physicians and hospital credentials

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

    medical and healthcare-related terminology, especially in contexts about physicians, hospitals, and clinical settings.

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

    The neuron detects references to healthcare institutions and organizational structures—especially mentions of hospitals, physician practices, affiliations, and related administrative terms.

    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
    Customers
    -0.98
    Customer
    -0.90
    Metodo
    -0.76
    customers
    -0.75
    Europa
    -0.75
     customers
    -0.74
    Clients
    -0.73
    nicze
    -0.73
    customer
    -0.72
     Customers
    -0.72
    POSITIVE LOGITS
     physician
    1.69
     physicians
    1.69
     Physician
    1.58
     Physicians
    1.36
     doctors
    1.31
    Physician
    1.28
     Practice
    1.27
     practice
    1.26
     group
    1.25
    physician
    1.24
    Activations Density 0.055%

    No Known Activations