© 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. 1562
    Prev
    Next
    INDEX
    Explanations

    hypoglycemia

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

    medical terms related to hypoglycemia and blood glucose conditions.

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

    The neuron fires on mentions of glycemic conditions—especially the term “hypoglycemia.”

    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
     gangsters
    -0.82
     rainwater
    -0.82
    Flam
    -0.82
     inund
    -0.79
     clogging
    -0.77
     infla
    -0.75
     inflam
    -0.74
     legislators
    -0.74
     clog
    -0.72
    Grease
    -0.72
    POSITIVE LOGITS
     hypo
    1.93
     Hypo
    1.75
    Hypo
    1.65
    hypo
    1.53
     lows
    1.30
     low
    1.20
     hipo
    1.19
     Low
    1.09
    低
    1.05
     counter
    1.02
    Activations Density 0.070%

    No Known Activations