© 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. 34-GEMMASCOPE-RES-131K
    7. 62728
    Prev
    Next
    INDEX
    Explanations

    law or agreement

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

    This neuron specifically picks up on the legal‐boilerplate language in comment headers—most strongly the occurrences of “applicable law” (and related license terms) in Apache‐style license blocks.

    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
     Nef
    -0.66
     good
    -0.65
    熱
    -0.65
    moor
    -0.64
    Recover
    -0.63
    ồi
    -0.63
     علمی
    -0.61
     Bride
    -0.60
    Quellen
    -0.60
     Joe
    -0.60
    POSITIVE LOGITS
    atorics
    0.71
    捋
    0.67
     dengue
    0.66
     suiker
    0.66
     foran
    0.65
    余额
    0.64
     AWD
    0.63
     Disqus
    0.63
     خاصية
    0.63
    Иск
    0.63
    Activations Density 0.129%

    No Known Activations