© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39883
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_l0_medium
    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
     Parish
    0.51
    tevõ
    0.49
    
    0.46
     parishioners
    0.46
    瓴
    0.45
     sbParams
    0.44
    運営
    0.43
     ينت
    0.43
     keV
    0.43
    籃
    0.43
    POSITIVE LOGITS
     regex
    0.81
    regex
    0.75
     pattern
    0.65
     Regex
    0.65
    Regex
    0.61
    pattern
    0.60
    正则表达式
    0.58
     패턴
    0.58
     patterns
    0.56
    patterns
    0.55
    Activations Density 0.091%

    No Known Activations