© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99783
    Prev
    Next
    INDEX
    Explanations

    diabetic medical conditions

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

    The neuron detects the word "diabetic" and diabetes-related medical terminology.

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

    The neuron primarily detects mentions of the term “diabetic” (i.e., references to diabetes-related conditions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    푆
    -2.98
    希望能
    -2.66
    लब्
    -2.63
     intertw
    -2.56
     catapult
    -2.34
     shimmering
    -2.33
    嵓
    -2.33
     eer
    -2.28
     occas
    -2.28
    甗
    -2.27
    POSITIVE LOGITS
    When
    2.67
    과
    2.66
    ؟
    2.52
     touted
    2.48
    Only
    2.44
    啭
    2.41
    What
    2.41
    Here
    2.39
    One
    2.39
     octombrie
    2.38
    Activations Density 0.010%

    No Known Activations