© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 31091
    Prev
    Next
    INDEX
    Explanations

    regular expression matching

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     阅读
    0.42
    Gd
    0.42
    SMA
    0.39
    ترض
    0.39
    वित
    0.39
    Vij
    0.39
     ઘ
    0.38
    粓
    0.38
    Highly
    0.38
     ایکسپریس
    0.38
    POSITIVE LOGITS
     re
    0.68
     r
    0.52
     os
    0.44
     ре
    0.44
     collections
    0.43
     plat
    0.42
     spoons
    0.41
     compiled
    0.41
     Re
    0.40
    re
    0.40
    Activations Density 0.003%

    No Known Activations