© 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. 79399
    Prev
    Next
    INDEX
    Explanations

    go command followed by action

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

    This neuron identifies code tokens—things like programming keywords (e.g. RUN, COPY, FROM), identifiers, and numeric literals—i.e. snippets of source-code syntax.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Symfony
    -0.82
     Rada
    -0.73
    PYTHON
    -0.72
     javascript
    -0.70
     Fluids
    -0.69
    Horn
    -0.69
     Rück
    -0.69
     trait
    -0.68
    BoxLayout
    -0.68
    斩
    -0.68
    POSITIVE LOGITS
    PACKAGE
    1.13
     GOR
    1.02
     package
    1.02
     Go
    0.98
     packages
    0.95
    Go
    0.94
     GO
    0.90
    fetchall
    0.86
    GO
    0.85
    testdata
    0.85
    Activations Density 0.196%

    No Known Activations