© 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. 22-GEMMASCOPE-RES-131K
    7. 127876
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting C/C++‐style single‐line comment markers (the “//” and accompanying comment text).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    Copyright notices in code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Before
    -1.15
     of
    -1.10
     when
    -1.09
     some
    -1.08
     Some
    -1.06
     legendary
    -1.06
     here
    -1.04
     before
    -1.01
     Every
    -1.00
     glorious
    -1.00
    POSITIVE LOGITS
     évé
    1.27
     rése
    1.26
     defStyle
    1.13
    ulir
    1.13
     Voilà
    1.13
     EVEN
    1.10
     sû
    1.08
    怎么回事
    1.05
     corriger
    1.05
    presented
    1.04
    Activations Density 0.025%

    No Known Activations