© 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. 13736
    Prev
    Next
    INDEX
    Explanations

    code syntax opening delimiters

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

    This neuron fires on programming-language identifiers and keywords—i.e. function/method names and reserved words in code.

    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
     "
    -1.13
    acchi
    -1.13
     những
    -1.13
     их
    -1.11
     leurs
    -1.09
     \"
    -1.07
     bulunan
    -1.03
    ictionary
    -1.02
     “
    -0.96
     ihren
    -0.95
    POSITIVE LOGITS
     it
    1.45
     this
    1.30
     massimo
    0.96
     bekämp
    0.94
    دکتر
    0.93
    verständ
    0.93
    軼
    0.93
    توضی
    0.91
     you
    0.90
    に追加
    0.90
    Activations Density 0.040%

    No Known Activations