Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8332
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and specific terminology

    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_34/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
     wolle
    -1.14
     while
    -1.00
     Durée
    -0.99
    While
    -0.91
     ahora
    -0.91
    диа
    -0.91
    égorie
    -0.90
     automne
    -0.87
    ԝ
    -0.87
     Métro
    -0.85
    POSITIVE LOGITS
     notably
    1.11
    Contribute
    1.02
     orientations
    1.00
     repugnant
    0.96
     Mô
    0.94
     roy
    0.94
     hesitating
    0.93
     fortemente
    0.90
     celib
    0.88
     asserting
    0.87
    Activations Density 0.000%

    No Known Activations