© 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. 10-GEMMASCOPE-RES-131K
    7. 120167
    Prev
    Next
    INDEX
    Explanations

    function definitions

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

    the closing of comment blocks in code, specifically the `*/` token that ends multi-line comments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects the end-of-block-comment marker (`*/`) in source 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_10/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
     ancienne
    -1.79
    𝟭
    -1.78
    tedì
    -1.75
     enmar
    -1.72
     abraz
    -1.69
    และ
    -1.63
     schnelle
    -1.57
    𝗠
    -1.56
     récomp
    -1.55
     rempli
    -1.55
    POSITIVE LOGITS
    4
    1.86
    1
    1.79
    u
    1.78
    l
    1.66
    na
    1.63
     should
    1.63
     when
    1.62
     which
    1.61
     are
    1.59
    6
    1.59
    Activations Density 0.004%

    No Known Activations