© 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. 93239
    Prev
    Next
    INDEX
    Explanations

    hospital and medical services

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

    content related to healthcare services, medical facilities, and insurance providers.

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

    The neuron detects definitional or purpose‐stating phrases that specify “for X” relationships—i.e. descriptions of services or roles provided for a particular group or function.

    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
     insurance
    -0.82
    ⌓
    -0.73
    وذ
    -0.69
     their
    -0.68
     años
    -0.67
     waitFor
    -0.67
    िश
    -0.66
     L
    -0.66
     subjec
    -0.66
    At
    -0.65
    POSITIVE LOGITS
    INGER
    1.09
    Treat
    0.94
    Benefit
    0.91
    toByteArray
    0.90
     viſ
    0.87
     eksper
    0.86
     expenses
    0.86
     services
    0.86
     konsult
    0.86
     dali
    0.85
    Activations Density 0.025%

    No Known Activations