© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64707
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs

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

    The neuron is triggered by code identifiers—named tokens like class/module names, version tags, constants, and other capitalized or technical symbols in source files.

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

    No Comments

    Negative Logits
    čili
    -0.99
     podstawie
    -0.95
     Händler
    -0.89
     armées
    -0.89
     reconnu
    -0.89
     Dinamarca
    -0.88
     procede
    -0.88
    说过
    -0.87
     where
    -0.86
     prisão
    -0.85
    POSITIVE LOGITS
     to
    1.09
    2
    0.97
    5
    0.96
    etro
    0.93
    ledem
    0.91
    8
    0.90
    roy
    0.88
    7
    0.88
    stru
    0.87
     roy
    0.85
    Activations Density 0.001%

    No Known Activations