© 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. 22746
    Prev
    Next
    INDEX
    Explanations

    code comments and metadata

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

    This neuron detects numeric tokens inside parentheses (e.g. numbers in comments).

    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
    <td>
    -2.75
    </b>
    -2.27
    几乎
    -1.81
    镡
    -1.81
    是
    -1.77
    啊
    -1.75
    </sup>
    -1.66
    US
    -1.66
     fiabilidad
    -1.65
    vrouw
    -1.63
    POSITIVE LOGITS
    ).
    2.31
     ';
    2.06
    妘
    2.03
    𝄆
    1.91
    鲣
    1.88
    The
    1.81
     temprano
    1.74
     includes
    1.72
    𓄹
    1.71
    下一篇
    1.70
    Activations Density 0.127%

    No Known Activations