© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107601
    Prev
    Next
    INDEX
    Explanations

    blood samples anticoagulant draw

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

    scientific content related to blood samples, serum, plasma, and anticoagulants in medical research.

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

    The neuron activates on tokens found in biomedical methods sections—particularly quantitative measurement and sample-preparation terminology.

    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
    Kamer
    -0.80
     imported
    -0.79
     carbonyl
    -0.78
     Kamer
    -0.76
    Import
    -0.72
    жень
    -0.71
    hatt
    -0.70
    Ответы
    -0.70
    ַח
    -0.68
     Import
    -0.68
    POSITIVE LOGITS
     anticoag
    1.45
     blood
    1.43
     EDTA
    1.38
     heparin
    1.22
     tubes
    1.19
     venous
    1.15
     Blood
    1.13
     draw
    1.13
    Blood
    1.13
    blood
    1.06
    Activations Density 0.104%

    No Known Activations