© 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. 22-GEMMASCOPE-RES-131K
    7. 16770
    Prev
    Next
    INDEX
    Explanations

    programming identifiers

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

    The neuron fires on programming‐code tokens—especially identifiers, method names, and other code symbols—marking segments of source 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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Just
    -0.95
    ントランス
    -0.93
     simply
    -0.90
    &
    -0.90
    textit
    -0.89
    ゆき
    -0.89
    ",
    -0.85
     zak
    -0.84
     caminos
    -0.84
     head
    -0.84
    POSITIVE LOGITS
    좆
    1.09
     squa
    1.04
     možnost
    1.03
     сексу
    0.99
     AMPL
    0.99
    rawdź
    0.98
     ところ
    0.97
     pixie
    0.97
     GreatSchools
    0.94
     Федера
    0.94
    Activations Density 0.039%

    No Known Activations