© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59567
    Prev
    Next
    INDEX
    Explanations

    coronary, corona, coronado

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

    This neuron detects variations of the word "coronary" and "corona", particularly in medical and scientific contexts.

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

    The neuron is detecting occurrences of the character sequence “coron” (as in “coronary,” “Coron,” or “Corona”).

    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
    Bibliography
    -0.72
    janja
    -0.70
    euvres
    -0.70
     earbuds
    -0.69
     Sheldon
    -0.69
    ชาติ
    -0.68
    ческие
    -0.68
     spôso
    -0.68
     každý
    -0.68
     auditory
    -0.68
    POSITIVE LOGITS
    CORO
    0.81
    antee
    0.80
     Coro
    0.79
     Coron
    0.75
     recurrir
    0.75
     coron
    0.75
    Virus
    0.74
     Coronation
    0.73
     crowns
    0.72
    bong
    0.72
    Activations Density 0.044%

    No Known Activations