© 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. 127615
    Prev
    Next
    INDEX
    Explanations

    python file extensions

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

    This neuron activates on instances of “py” marking Python filenames or extensions.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -2.64
     They
    -2.50
     ikke
    -2.33
    </sup>
    -2.28
    </em>
    -2.22
    </h3>
    -2.19
     ")
    -2.17
     pensar
    -2.13
     “
    -2.11
    辔
    -2.11
    POSITIVE LOGITS
    {
    2.48
    將軍
    2.36
    老闆
    2.34
    面對
    2.33
     You
    2.31
    聽到
    2.27
    ᡥ
    2.25
    uję
    2.22
    紓
    2.22
     this
    2.17
    Activations Density 0.007%

    No Known Activations