© 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. 10-GEMMASCOPE-RES-131K
    7. 100686
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis or brace

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

    backslashes used as escape characters in code or LaTeX syntax.

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

    The neuron detects literal backslash characters (the “\” escape token) in the text.

    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
     espl
    -1.71
    !")
    -1.70
    翃
    -1.66
    !";
    -1.65
    퐼
    -1.64
    !
    -1.63
    t
    -1.61
    焢
    -1.61
    !</
    -1.51
     mancher
    -1.51
    POSITIVE LOGITS
    ).
    2.39
    3
    2.02
     then
    1.98
     in
    1.88
    6
    1.85
    ?
    1.82
    驁
    1.77
    5
    1.77
    潟
    1.72
     Voraussetzung
    1.67
    Activations Density 0.007%

    No Known Activations