© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127336
    Prev
    Next
    INDEX
    Explanations

    heat transfer and exchange

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ௅
    -1.60
    Ꮷ
    -1.57
     pitié
    -1.43
    ),
    
    -1.43
     anthology
    -1.42
    ridor
    -1.41
    ⎔
    -1.41
     vás
    -1.41
     scented
    -1.41
    dients
    -1.39
    POSITIVE LOGITS
     with
    1.55
    ↵↵
    1.54
     of
    1.52
    2
    1.49
    z
    1.38
     并
    1.34
    re
    1.33
     then
    1.33
     -
    1.32
     barring
    1.32
    Activations Density 0.038%

    No Known Activations