© 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. 40109
    Prev
    Next
    INDEX
    Explanations

    code comments and descriptions

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

    The neuron fires on code comment markers and documentation tags (e.g. “///”, “/**”, “*”, XML doc tags like `<summary>`) 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
     ExecuteAsync
    -1.21
     its
    -1.03
     cờ
    -1.02
     their
    -0.99
    的所有
    -0.98
     acondicionado
    -0.93
    ですよね
    -0.93
     afirmar
    -0.91
     veľa
    -0.89
     voetballer
    -0.88
    POSITIVE LOGITS
    どん
    1.02
    1.00
     speciale
    1.00
    是大
    0.99
     institu
    0.98
    (
    0.96
    һ
    0.95
    —
    0.93
    HttpClient
    0.93
    acer
    0.92
    Activations Density 0.003%
    No Known Activations