© 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. 45358
    Prev
    Next
    INDEX
    Explanations

    medicines

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

    words and contexts related to medications, drugs, and pharmaceuticals.

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

    The neuron activates on occurrences of the word “medicine” (and its plural or closely related forms).

    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
    s
    -3.47
    </sup>
    -2.52
    i
    -2.45
    ”、“
    -2.31
    <td>
    -2.28
     hecho
    -2.27
    k
    -2.17
    </b>
    -2.14
    要在
    -2.09
    拶
    -2.09
    POSITIVE LOGITS
    躥
    2.22
     Js
    2.06
    觊
    2.03
     persino
    1.93
    Apparently
    1.91
    崀
    1.91
     这个
    1.88
     Segurança
    1.87
    墙壁
    1.87
    臵
    1.86
    Activations Density 0.006%

    No Known Activations