© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12910
    Prev
    Next
    INDEX
    Explanations

    regular expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    邰
    0.50
     stewardship
    0.48
    醸
    0.45
     fizi
    0.43
    មា
    0.43
    दशी
    0.43
    📤
    0.43
     procédure
    0.42
    涼
    0.42
     cooling
    0.42
    POSITIVE LOGITS
     regex
    1.60
     Regex
    1.51
    regex
    1.50
    Regex
    1.36
    正则表达式
    1.30
    REGEX
    1.17
     regexp
    1.10
    pattern
    1.02
     pattern
    1.01
     RegExp
    1.00
    Activations Density 0.035%

    No Known Activations