© 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. 22-GEMMASCOPE-RES-131K
    7. 64454
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and code contexts

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ar
    -1.67
     班
    -1.48
     药
    -1.46
     to
    -1.43
     —
    -1.41
    ‘
    -1.34
     饭
    -1.28
     in
    -1.28
    其妙
    -1.27
    리
    -1.27
    POSITIVE LOGITS
    を見つけ
    1.62
     erleich
    1.52
     divinely
    1.50
    
    1.49
    — 
    1.47
     unbeatable
    1.45
     olvidado
    1.45
     estn
    1.45
    **.
    1.43
     چقدر
    1.42
    Activations Density 0.001%

    No Known Activations