© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39883
    Prev
    Next
    INDEX
    Explanations

    regex

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

    regex matching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    瓴
    0.50
    ランキング
    0.48
    
    0.46
    運輸
    0.46
     shipbuilding
    0.45
     Parish
    0.44
     pledging
    0.44
    祢
    0.44
     витами
    0.44
     ينت
    0.44
    POSITIVE LOGITS
     regex
    1.07
    regex
    1.00
     Regex
    0.98
    Regex
    0.86
    正则表达式
    0.82
     regexp
    0.80
    regexp
    0.74
    REGEX
    0.74
    pattern
    0.73
     pattern
    0.71
    Activations Density 0.010%

    No Known Activations