© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15125
    Prev
    Next
    INDEX
    Explanations

    wound dressing and medical supplies

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

    medical dressing and bandage terms.

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

    This neuron detects words referring to wound‐covering or medical dressing items (e.g. bandage, dressing, patch, tourniquet).

    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
    en
    -2.09
     he
    -1.91
    <tr>
    -1.84
    </h3>
    -1.80
    n
    -1.72
    an
    -1.67
    )
    -1.66
    馀
    -1.65
    fifty
    -1.65
    ჻
    -1.63
    POSITIVE LOGITS
    后续
    1.94
    ęd
    1.76
     senere
    1.73
     født
    1.73
    Kemudian
    1.72
     Testamento
    1.67
     燒
    1.65
    zeitung
    1.64
    我先
    1.63
     solicitar
    1.62
    Activations Density 0.003%

    No Known Activations