© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11228
    Prev
    Next
    INDEX
    Explanations

    software library licenses

    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
    Not in Any Lists

    No Comments

    Negative Logits
    momile
    -1.05
     Vielzahl
    -1.04
    我们
    -1.04
     noastră
    -0.99
     refirió
    -0.99
    人的
    -0.98
     refiere
    -0.95
     物語
    -0.94
     crusher
    -0.93
     població
    -0.91
    POSITIVE LOGITS
     cerim
    0.95
     Aralık
    0.95
    Beispiele
    0.94
     libero
    0.94
     originale
    0.94
     WARRANTY
    0.92
    Exemples
    0.91
    ண
    0.91
     سرب
    0.90
     Универ
    0.89
    Activations Density 0.169%

    No Known Activations