© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114163
    Prev
    Next
    INDEX
    Explanations

    Android XML layout or jQuery

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

    the opening tag "RelativeLayout" in Android XML layout files or references to jQuery in code.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    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
    Negative Logits
    a
    -2.67
     For
    -2.58
     είναι
    -2.56
     While
    -2.52
     Since
    -2.45
     =
    -2.44
     By
    -2.34
    可能
    -2.31
    而
    -2.28
    8
    -2.23
    POSITIVE LOGITS
    谖
    2.83
    瞜
    2.81
    皛
    2.75
     皇族
    2.72
    
    2.70
    錞
    2.70
    俛
    2.67
    
    2.58
    盌
    2.56
     唯美
    2.53
    Activations Density 0.006%

    No Known Activations