© 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. 24917
    Prev
    Next
    INDEX
    Explanations

    #pragma mark / #region / Constructors

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

    This neuron detects code “section” or “region” markers and separators—preprocessor directives like `#pragma mark` or `#region` and their accompanying dashes or dividers.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    久し
    -1.82
     Usar
    -1.76
    あぁ
    -1.74
    ☡
    -1.74
     rústico
    -1.72
     Empieza
    -1.69
    máy
    -1.68
    
    -1.68
    Če
    -1.66
     VOUS
    -1.64
    POSITIVE LOGITS
    </em>
    2.13
    </strong>
    1.99
     with
    1.81
    L
    1.80
    </b>
    1.80
    a
    1.79
    f
    1.78
     -
    1.75
     before
    1.73
    j
    1.73
    Activations Density 0.002%

    No Known Activations