© 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. 19709
    Prev
    Next
    INDEX
    Explanations

    Alzheimer's disease (AD)

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

    references to Alzheimer's disease in scientific or medical texts.

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

    The neuron detects mentions of neurodegenerative diseases—especially “disease” labels like Alzheimer’s disease, Parkinson’s disease, and their abbreviations.

    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
    轫
    -1.69
    賬
    -1.53
     بهداشتی
    -1.48
    恢復
    -1.45
    紧接着
    -1.43
    issão
    -1.43
     gloria
    -1.42
    たっぷ
    -1.41
    随后
    -1.38
    犸
    -1.38
    POSITIVE LOGITS
    你有
    1.56
     verdaderamente
    1.46
    ཫ
    1.38
    냑
    1.37
     chiaro
    1.35
     probablemente
    1.34
     estrictamente
    1.33
     But
    1.32
     derselbe
    1.30
     your
    1.29
    Activations Density 0.064%

    No Known Activations