© 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. 79545
    Prev
    Next
    INDEX
    Explanations

    code syntax structures

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

    The neuron fires on programming‐specific jargon—things like API or method names, file/extension tokens, and other code‐related terms.

    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
    ابراین
    -0.99
    </b>
    -0.96
    со
    -0.95
    理石
    -0.94
    ATIVO
    -0.93
    净化
    -0.93
    一周
    -0.92
    攷
    -0.91
    合影
    -0.90
    дан
    -0.90
    POSITIVE LOGITS
    _
    2.92
    \_
    1.73
    @
    1.34
    ://
    1.30
    ="
    1.25
     stratég
    1.24
    ();
    1.23
    (),
    1.16
    ...@
    1.15
    ()
    1.14
    Activations Density 0.627%

    No Known Activations