© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21484
    Prev
    Next
    INDEX
    Explanations

    burden of disease

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

    The neuron detects the phrase "burden of disease" and related public health terminology in scientific or medical contexts.

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

    The neuron responds to the phrase “burden of …,” marking mentions of the epidemiological or disease burden of a condition.

    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
    葙
    -3.61
    ⸰
    -3.22
    The
    -2.98
    ?”
    -2.97
    
    -2.92
    🧌
    -2.91
    鲧
    -2.83
    
    -2.75
    𖣘
    -2.66
    甞
    -2.63
    POSITIVE LOGITS
     étab
    2.91
    </b>
    2.78
    izing
    2.63
    趼
    2.39
     
    2.36
    傀
    2.20
    ん
    2.17
    to
    2.13
     To
    2.06
    矜
    2.06
    Activations Density 0.004%

    No Known Activations