© 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. 103367
    Prev
    Next
    INDEX
    Explanations

    regular expressions or code context

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

    backslash characters in technical or mathematical text (LaTeX formatting, regex patterns, and code).

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

    This neuron detects regular‐expression literals (slash‐delimited regex patterns) in 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
    Ꮉ
    -3.09
     If
    -2.66
     股份
    -2.58
    猡
    -2.52
    所需的
    -2.52
    ],
    -2.52
    獁
    -2.48
    鄖
    -2.42
    StoryboardSegue
    -2.42
    k
    -2.39
    POSITIVE LOGITS
    ا
    3.20
     ridiculously
    2.88
     малень
    2.86
    e
    2.83
    在
    2.78
    “
    2.75
    ну
    2.72
     extravag
    2.67
    1
    2.67
    са
    2.61
    Activations Density 0.001%

    No Known Activations