© 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. 6790
    Prev
    Next
    INDEX
    Explanations

    agreed to in writing

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

    The neuron detects occurrences of the boilerplate clause “agreed to in writing” (especially the word “writing”) in license headers.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    تیجه
    -1.80
     blant
    -1.71
     \
    -1.62
    ’
    -1.58
     enorme
    -1.54
    嚒
    -1.53
    上に
    -1.46
    днако
    -1.45
     बहुत
    -1.45
    (
    -1.45
    POSITIVE LOGITS
    酲
    2.06
     and
    1.75
    诳
    1.74
     is
    1.67
     which
    1.63
    猹
    1.59
    齪
    1.59
     destacado
    1.56
    .」
    1.54
    ";
    1.52
    Activations Density 0.017%

    No Known Activations