© 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. 3330
    Prev
    Next
    INDEX
    Explanations

    code comments and file paths

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

    This neuron spotlights code section delimiters—lines that end or close blocks (e.g. comment-end “*/”, closing tags like “</script>”, and similar boundary markers).

    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
    ḩ
    -1.07
    дется
    -0.96
    OIS
    -0.94
    järvi
    -0.91
     there
    -0.89
     történ
    -0.87
     mater
    -0.87
     fortfarande
    -0.86
    Արտաքին
    -0.86
     as
    -0.85
    POSITIVE LOGITS
     mögliche
    1.20
     plazos
    1.17
     carcasa
    1.13
     ventilación
    1.10
     öffentliche
    1.09
    filepath
    1.07
     ganancia
    1.07
     vuelva
    1.05
    utnik
    1.05
    ;<
    1.05
    Activations Density 0.001%

    No Known Activations