© 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. 99606
    Prev
    Next
    INDEX
    Explanations

    medical device infusion and insertion

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

    medical equipment and procedures related to needles, catheters, and medical insertion devices.

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

    This neuron detects technical biomedical terms—especially clinical procedures, devices, and measurement methods (e.g. catheterization, ultrasound, needle aspiration, specific gauges, chi-square tests) used in medical study reports.

    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
    Brush
    -0.81
     IFTTT
    -0.78
     köy
    -0.77
     ajustable
    -0.77
    numRows
    -0.76
     Normandie
    -0.74
     hôtels
    -0.73
     faculté
    -0.73
    ViewFeatures
    -0.73
     Sí
    -0.73
    POSITIVE LOGITS
     site
    1.34
     sites
    1.17
     bevel
    1.10
     محل
    0.98
     technique
    0.96
    SITE
    0.96
    site
    0.94
    tése
    0.91
    sites
    0.91
    ipun
    0.89
    Activations Density 0.098%

    No Known Activations