© 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. 34-GEMMASCOPE-RES-131K
    7. 82638
    Prev
    Next
    INDEX
    Explanations

    healthcare providers and delivery

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

    healthcare-related terms and concepts.

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

    The neuron activates primarily on the term “healthcare” (including its variants like “health care”).

    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
     cares
    -0.99
     Cares
    -0.92
     cared
    -0.91
     CARE
    -0.87
     fancies
    -0.85
     steals
    -0.84
     care
    -0.84
     torno
    -0.84
    コミ
    -0.83
     bemerk
    -0.83
    POSITIVE LOGITS
     provider
    1.59
     providers
    1.56
    providers
    1.26
     delivery
    1.21
     Provider
    1.20
    Providers
    1.19
    provider
    1.16
    Provider
    1.11
     professionals
    1.10
    delivery
    1.09
    Activations Density 0.020%

    No Known Activations