© 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. 75585
    Prev
    Next
    INDEX
    Explanations

    cesarean section

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

    The neuron is looking for variations of the term "cesarian" or "cesarean" section and other medical terminology.

    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_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
    чия
    -0.88
     caribou
    -0.75
    stimulus
    -0.73
     though
    -0.73
     Choice
    -0.72
    lichung
    -0.72
     sentito
    -0.71
    -[
    -0.70
    Grady
    -0.68
     integrity
    -0.66
    POSITIVE LOGITS
     Ces
    0.88
     ces
    0.87
    Ces
    0.83
    ces
    0.75
    pit
    0.71
     effekt
    0.71
    égard
    0.71
     salad
    0.71
     griechischen
    0.69
    QUANT
    0.69
    Activations Density 0.029%

    No Known Activations