© 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. 111323
    Prev
    Next
    INDEX
    Explanations

    von Willebrand factor

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

    The neuron detects medical/scientific terms related to blood factors, particularly "von Willebrand factor" and anatomical structures.

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

    The neuron is specifically detecting mentions of the blood-clotting protein “von Willebrand factor.”

    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
    .
    -2.31
    ſſel
    -2.25
    uded
    -1.91
    {
    -1.83
    ties
    -1.80
    ↵↵
    -1.80
     {
    -1.78
    lllllll
    -1.78
    to
    -1.77
     hà
    -1.77
    POSITIVE LOGITS
    avorite
    2.19
    inston
    2.09
     Alongside
    2.05
     Both
    2.05
    嵛
    1.97
    磲
    1.95
     Either
    1.95
    karet
    1.87
     Recently
    1.85
     "";
    1.84
    Activations Density 0.053%

    No Known Activations