© 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. 10-GEMMASCOPE-RES-131K
    7. 39194
    Prev
    Next
    INDEX
    Explanations

    incidence of medical conditions

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

    The neuron identifies phrases related to incidence rates and prevalence of medical conditions in scientific literature.

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

    The neuron detects epidemiological statistics—especially incidence/prevalence figures and other numeric rates—in biomedical text.

    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
     {
    -1.84
    怍
    -1.63
     gegebenen
    -1.61
    蓐
    -1.59
     dimensiones
    -1.59
    ꦗ
    -1.56
     the
    -1.54
    ꦫ
    -1.53
    "})
    -1.52
     columnas
    -1.52
    POSITIVE LOGITS
     in
    1.94
     on
    1.62
     at
    1.56
    e
    1.50
    توضیحات
    1.48
    </sup>
    1.46
    Andere
    1.43
    侂
    1.43
     bahaya
    1.41
     doesnt
    1.39
    Activations Density 0.212%

    No Known Activations