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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28051
    Prev
    Next
    INDEX
    Explanations

    code keywords and punctuation

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

    The neuron fires on code tokens that introduce or reference object‐oriented members—e.g. static method declarations, property/method names (like onEnter or $inject), prototype assignments, and other member‐access or definition sites.

    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
     saati
    -1.30
     siè
    -1.17
     stili
    -1.16
    婠
    -1.15
     suivent
    -1.13
     FÜR
    -1.11
     auraient
    -1.11
     brachten
    -1.10
     différentes
    -1.09
     puissent
    -1.08
    POSITIVE LOGITS
     on
    1.48
    。　
    1.18
     with
    1.09
     should
    1.01
     soothing
    1.00
     requires
    0.98
     use
    0.97
     verhindern
    0.97
     is
    0.97
     troubling
    0.96
    Activations Density 0.002%

    No Known Activations