© 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. 3510
    Prev
    Next
    INDEX
    Explanations

    Q A format

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

    This neuron detects snake_case identifiers (tokens containing underscores) in code.

    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
     trying
    -1.27
     hoping
    -1.11
     Trying
    -1.09
     aims
    -1.08
     hope
    -1.06
     hopes
    -1.03
     attempting
    -0.89
     tries
    -0.88
     aiming
    -0.87
     try
    -0.87
    POSITIVE LOGITS
    [
    1.14
    ][
    1.11
    [][
    1.00
     paramètres
    0.79
     rimanere
    0.79
     comportements
    0.79
     hầm
    0.78
    Etsy
    0.78
     problèmes
    0.76
     propriétés
    0.76
    Activations Density 0.021%

    No Known Activations