© 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. 8904
    Prev
    Next
    INDEX
    Explanations

    von Willebrand factor

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

    acronyms, names of organizations, and specialized scientific/technical terms.

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

    The neuron is detecting numeric measurement values—specifically tokens representing numbers (often with decimals) in scientific or data contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    proper nouns and acronyms, especially technical or biomedical names.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    proper nouns and abbreviations, particularly technical terms, brand names, and scientific/medical terminology.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    丏
    -3.30
    ]
    -2.83
     Hinblick
    -2.53
    豨
    -2.48
    って思
    -2.48
    怱
    -2.47
     Certificado
    -2.41
     charla
    -2.41
     When
    -2.39
     mauva
    -2.39
    POSITIVE LOGITS
    d
    2.67
    as
    2.59
    渽
    2.58
    ’
    2.56
     zwanzig
    2.34
    6
    2.33
     anstatt
    2.28
    and
    2.27
    ?!?
    2.19
     tht
    2.17
    Activations Density 0.086%

    No Known Activations