© 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. 380
    Prev
    Next
    INDEX
    Explanations

    Notre Dame, Daphne DuMaurier

    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
     erwähnten
    -2.50
    􀂃
    -2.48
     nordrhein
    -2.47
     We
    -2.39
     gewünschten
    -2.39
     genannten
    -2.38
     industrias
    -2.36
     agencias
    -2.36
     betreffenden
    -2.33
     aérienne
    -2.23
    POSITIVE LOGITS
    ↵↵
    2.63
    >");
    
    2.39
    >");
    2.34
     alban
    2.34
    [
    2.27
    และ
    2.19
     comboBox
    2.19
     we
    2.19
     GOLF
    2.19
    ра
    2.17
    Activations Density 0.001%

    No Known Activations