© 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. 83950
    Prev
    Next
    INDEX
    Explanations

    glucose and blood pressure levels

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

    terms related to blood glucose levels, particularly in the context of diabetes research and monitoring.

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

    The neuron detects mentions of blood-related clinical measurements (e.g. blood glucose, blood pressure, lipid levels).

    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
     Vallejo
    -0.88
     xuất
    -0.86
    ܂
    -0.85
    都没
    -0.82
     évident
    -0.82
     będ
    -0.81
    STEN
    -0.81
     yoğun
    -0.80
    ticion
    -0.80
    danh
    -0.79
    POSITIVE LOGITS
     levels
    2.28
    levels
    1.58
     Levels
    1.55
     level
    1.52
     readings
    1.45
     LEVELS
    1.44
    Levels
    1.38
    LEVEL
    1.19
     Readings
    1.17
     reading
    1.13
    Activations Density 0.045%

    No Known Activations