© 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. 33276
    Prev
    Next
    INDEX
    Explanations

    code syntax punctuation

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

    This neuron detects programming identifiers—especially CamelCase names and capitalized API/method tokens.

    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
     now
    -1.05
     intense
    -0.96
     heridas
    -0.96
    новништво
    -0.90
     other
    -0.86
     bright
    -0.86
     dramatic
    -0.84
     intensa
    -0.84
     should
    -0.84
     their
    -0.84
    POSITIVE LOGITS
     RÉ
    1.05
    āb
    1.00
     vā
    0.96
    شفى
    0.96
     Tél
    0.93
     docteur
    0.93
     Aroma
    0.93
    鰱
    0.91
     hany
    0.91
     Jé
    0.91
    Activations Density 0.003%

    No Known Activations