© 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. 10-GEMMASCOPE-RES-131K
    7. 129736
    Prev
    Next
    INDEX
    Explanations

    medical infusion

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

    medical terms related to infusion or infusion devices used for drug delivery.

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

    The neuron activates on mentions of “infusion” (and its variants) in the context of medical devices or drug delivery systems.

    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
    킁
    -2.77
    ₶
    -2.73
    ౮
    -2.70
    actéristi
    -2.70
    these
    -2.58
    n
    -2.55
    ጴ
    -2.50
    ᠂
    -2.48
     ส์
    -2.44
    🫃
    -2.42
    POSITIVE LOGITS
     of
    2.28
    ,
    2.17
    $
    2.13
     
    2.08
    лил
    2.00
     quaint
    1.91
     And
    1.88
     phénom
    1.88
    ⃙
    1.87
     At
    1.82
    Activations Density 0.011%

    No Known Activations