© 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. 58258
    Prev
    Next
    INDEX
    Explanations

    Public followed by financial, folder, key, license, file, method

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     VERY
    -3.14
     they
    -3.13
     بالإضافة
    -2.98
     
    -2.95
      
    -2.94
     marvelous
    -2.80
     startling
    -2.73
     astute
    -2.69
     beberapa
    -2.66
     nonchal
    -2.64
    POSITIVE LOGITS
     शुर
    4.13
    ))$_
    3.66
    倨
    3.33
    
    3.30
    ઁ
    3.27
     ()
    3.19
    इटम
    3.09
    鋮
    3.08
    屜
    3.05
    缫
    3.05
    Activations Density 0.054%

    No Known Activations