© 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. 108834
    Prev
    Next
    INDEX
    Explanations

    veterinary medical cases and anatomy

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

    text related to veterinary medicine and animal health topics.

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

    The neuron strongly activates on long, specialized scientific or medical terms (i.e. technical jargon) in veterinary/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_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
     providers
    -0.76
     physician
    -0.73
     scalp
    -0.69
     Physician
    -0.68
     strapped
    -0.67
    Specimen
    -0.66
    ưa
    -0.66
    Physician
    -0.64
    ЛЯ
    -0.63
     kapcsolat
    -0.63
    POSITIVE LOGITS
    Vet
    1.06
     veterinary
    1.06
     Veterinary
    1.03
     Vet
    1.02
     JAV
    0.99
    JAV
    0.94
    vet
    0.93
     владель
    0.93
    Owners
    0.92
     VETER
    0.91
    Activations Density 0.192%

    No Known Activations