© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38850
    Prev
    Next
    INDEX
    Explanations

    code comment markers

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

    This neuron fires on comment‐delimiter tokens (e.g. “//”, “#*”, “%-”, “<!--”, etc.) that mark the start of comments in various programming and markup languages.

    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
     or
    -2.73
     and
    -2.50
     undeniably
    -2.30
     marvellous
    -2.20
     any
    -2.14
     perplexing
    -2.09
     what
    -2.09
     &
    -2.06
     enormous
    -2.06
     three
    -2.03
    POSITIVE LOGITS
     análise
    2.11
     "*
    2.11
     suspensão
    2.05
     luscious
    2.05
    to
    2.03
     overly
    1.97
    ?"
    1.95
     accentu
    1.93
    ほうが
    1.91
     acclaimed
    1.91
    Activations Density 0.005%

    No Known Activations