© 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. 34-GEMMASCOPE-RES-131K
    7. 2049
    Prev
    Next
    INDEX
    Explanations

    diseases and viruses

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

    infectious diseases and medical conditions in epidemiological contexts.

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

    The neuron fires on specific disease names—particularly infectious-disease terms (e.g., influenza, tuberculosis, plague, malaria, dengue, Zika) often appearing in categorical listings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    BPM
    -0.87
    ẖ
    -0.86
     hume
    -0.86
    ciencia
    -0.84
     quod
    -0.80
    ʆ
    -0.78
    --
    -0.78
    "#
    -0.78
     مشارکت
    -0.76
     squares
    -0.75
    POSITIVE LOGITS
     measles
    2.25
     cholera
    2.11
     malaria
    2.05
     Ebola
    1.91
     polio
    1.91
     tuberculosis
    1.87
     hepatitis
    1.81
     rabies
    1.81
     dengue
    1.79
     influenza
    1.77
    Activations Density 0.300%

    No Known Activations