© 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. 22-GEMMASCOPE-RES-131K
    4. 71622
    Prev
    Next
    INDEX
    Explanations

    athletic performance and endurance

    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
    龛
    -1.37
     vinaigre
    -1.30
     السياس
    -1.19
     السيارات
    -1.17
     TRAFFIC
    -1.16
     portefeuille
    -1.16
    接続
    -1.15
     encargada
    -1.14
     comportement
    -1.13
     défi
    -1.13
    POSITIVE LOGITS
     during
    2.09
     training
    1.71
     performance
    1.63
     upcoming
    1.37
     your
    1.36
     athletes
    1.36
     endurance
    1.33
     campionato
    1.30
     both
    1.30
     increase
    1.30
    Activations Density 0.056%

    No Known Activations