© 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. 68715
    Prev
    Next
    INDEX
    Explanations

    programming keywords and methods

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

    The neuron activates on named program symbols—especially CamelCase or PascalCase identifiers (method names, class names, and other code symbols that start with a capital letter).

    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
    y
    -3.70
    -
    -3.59
    3
    -3.59
    2
    -3.56
    5
    -3.34
    ).
    -3.19
    c
    -3.11
    7
    -3.03
    4
    -2.97
    9
    -2.73
    POSITIVE LOGITS
    iniums
    2.84
     书法
    2.64
     voegen
    2.64
    apatalk
    2.50
    riors
    2.36
    葑
    2.34
    していました
    2.33
    翾
    2.33
     klikken
    2.31
     verwijzen
    2.31
    Activations Density 0.000%

    No Known Activations