© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68591
    Prev
    Next
    INDEX
    Explanations

    von Willebrand factor

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

    numbers appearing at the start of text sections, particularly version numbers or section numbers.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    Negative Logits
    ఽ
    -1.87
    ↵
    -1.80
    鼱
    -1.63
    崀
    -1.63
     различных
    -1.61
    ཊ
    -1.59
     quelconque
    -1.59
     wszystkich
    -1.59
     efectivos
    -1.58
     fiind
    -1.55
    POSITIVE LOGITS
     even
    2.19
    .
    2.16
     in
    2.13
     it
    2.02
     with
    1.85
     at
    1.85
     by
    1.82
     despite
    1.69
     you
    1.58
     There
    1.55
    Activations Density 0.001%

    No Known Activations