© 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. 19069
    Prev
    Next
    INDEX
    Explanations

    escaped parentheses

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

    This neuron detects regex escape sequences—specifically backslash‐escaped characters like “\(” and “\)”.

    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
    ]
    -2.73
     feiner
    -2.70
    珰
    -2.67
    }
    -2.66
    0
    -2.50
     besonderes
    -2.42
     vieler
    -2.36
    味は
    -2.33
    2
    -2.30
     sogen
    -2.27
    POSITIVE LOGITS
     otras
    2.39
    ка
    2.38
    秾
    2.28
    СЯ
    2.28
    öpfer
    2.13
    高达
    2.09
     digunakan
    2.08
    銠
    2.06
    oucí
    2.03
    柘
    2.02
    Activations Density 0.002%

    No Known Activations