© 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. 66672
    Prev
    Next
    INDEX
    Explanations

    non-English text

    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
     in
    -1.44
     with
    -0.98
     toward
    -0.97
     without
    -0.92
     cerdas
    -0.91
     and
    -0.90
     Towards
    -0.89
     but
    -0.89
     Toward
    -0.88
    scraper
    -0.87
    POSITIVE LOGITS
    以外の
    1.05
     unending
    1.02
    alism
    0.98
     .........
    0.97
     ピンク
    0.97
    专门
    0.95
     corriger
    0.94
     amd
    0.93
     женщины
    0.93
    vereign
    0.92
    Activations Density 0.035%

    No Known Activations