© 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. 22-GEMMASCOPE-RES-131K
    7. 35659
    Prev
    Next
    INDEX
    Explanations

    chronic medical conditions

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

    The neuron detects the word "chronic" in medical and scientific contexts, especially when referring to chronic diseases or conditions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     decidedly
    -2.91
    
    -2.61
     horrid
    -2.56
     REALLY
    -2.44
     ferocious
    -2.39
     crucial
    -2.39
    都想
    -2.39
     ส์
    -2.30
     exceedingly
    -2.30
     diversos
    -2.30
    POSITIVE LOGITS
    \_
    3.16
    ”，
    2.95
    ～～
    2.59
    w
    2.50
    ”？
    2.47
    Even
    2.47
    ！”
    2.31
    3
    2.28
     "..\..\
    2.28
    Every
    2.25
    Activations Density 0.034%

    No Known Activations