© 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. 90409
    Prev
    Next
    INDEX
    Explanations

    medical professions

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

    medical professional titles like surgeon, radiologist, cardiologist, and obstetrician.

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

    The neuron activates on terms naming medical specialists or professional titles (e.g. surgeon, radiologist, cardiologist, obstetrician, psychiatrist).

    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
     Qaeda
    -1.46
    édi
    -1.46
    umerable
    -1.41
    这不是
    -1.41
    onViewCreated
    -1.39
    bilisi
    -1.39
    vantaged
    -1.39
    henden
    -1.38
    haviours
    -1.35
    沕
    -1.35
    POSITIVE LOGITS
    邂
    1.18
    вості
    1.16
     burada
    1.14
     moglie
    1.13
     során
    1.13
     voyez
    1.13
     acolo
    1.13
    るところ
    1.12
     trouvez
    1.12
     impresora
    1.10
    Activations Density 0.078%

    No Known Activations