© 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. 123532
    Prev
    Next
    INDEX
    Explanations

    code comments and metadata

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

    personal names, particularly author names and usernames in code comments and documentation.

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

    The neuron detects occurrences of personal names in author or copyright bylines (e.g., names in file headers or comment blocks).

    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
     five
    -1.66
     and
    -1.57
    ᳝
    -1.54
     should
    -1.53
     must
    -1.48
     the
    -1.46
    裡的
    -1.44
     trampa
    -1.38
     eight
    -1.36
     cread
    -1.34
    POSITIVE LOGITS
    𨭎
    1.66
    殃
    1.61
    noons
    1.61
    also
    1.56
    𓏸
    1.54
    <!--
    1.52
    ̵
    1.51
     egreg
    1.50
     cultur
    1.48
    も多く
    1.48
    Activations Density 0.169%

    No Known Activations