© 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. 9921
    Prev
    Next
    INDEX
    Explanations

    medical professionals and visits

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

    references to medical professionals like "doctor," "docs," "GYN," "dermatologist," or "cardiologist" in healthcare contexts.

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

    The neuron fires on mentions of medical professionals’ titles (e.g. doctor, GP, dermatologist, cardiologist, vet).

    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
    </em>
    -1.84
     många
    -1.70
    ágeno
    -1.52
     occas
    -1.51
    𐐀
    -1.49
    ouncements
    -1.47
    健身
    -1.45
    ？】
    -1.45
    ötzlich
    -1.45
     frågor
    -1.45
    POSITIVE LOGITS
     himself
    1.91
     who
    1.70
     Ć
    1.48
     secoli
    1.48
    屺
    1.41
     folosi
    1.38
     avete
    1.38
     дописа
    1.35
    ための
    1.34
     there
    1.33
    Activations Density 0.036%

    No Known Activations