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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12045
    Prev
    Next
    INDEX
    Explanations

    URL encoding & HTML entities

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

    URL-encoded characters, particularly the percent sign followed by hexadecimal digits in encoded URLs.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -1.90
     with
    -1.66
     -
    -1.49
     
    -1.48
      
    -1.42
    1
    -1.39
     out
    -1.39
    ,
    -1.36
    ’
    -1.35
    '
    -1.32
    POSITIVE LOGITS
     they
    1.85
    閖
    1.78
    殽
    1.75
    
    1.73
     strategi
    1.73
    henge
    1.69
     kafe
    1.68
     diny
    1.67
     demokra
    1.60
    鱚
    1.60
    Activations Density 0.008%

    No Known Activations