© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113937
    Prev
    Next
    INDEX
    Explanations

    toxicology and ophthalmic terms

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

    scientific and medical terminology related to ophthalmology and toxicology.

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

    This neuron responds to specialized biomedical jargon—long technical terms (e.g. “toxicological,” “Toxicology,” “ophthalmic,” etc.) common in medical and toxicology literature.

    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
    I
    -3.02
     When
    -2.86
     Effectively
    -2.83
     Quando
    -2.61
     Ensuring
    -2.59
     Importantly
    -2.47
     During
    -2.45
     But
    -2.39
     Alongside
    -2.39
     durante
    -2.30
    POSITIVE LOGITS
    d
    2.48
    ﮨ
    2.47
     itſelf
    2.44
    z
    2.41
    ーズン
    2.41
    ,”
    2.39
     可爱
    2.38
    د
    2.25
    厖
    2.22
    市の
    2.17
    Activations Density 0.006%

    No Known Activations