© 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. 11229
    Prev
    Next
    INDEX
    Explanations

    HTML style tag

    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
     crudo
    -0.91
    ListBy
    -0.86
    fpath
    -0.85
     milion
    -0.84
    IdList
    -0.82
    人民共和国
    -0.82
    PMT
    -0.81
     financiers
    -0.80
     possi
    -0.79
    坚持
    -0.79
    POSITIVE LOGITS
     молока
    1.00
     khảo
    0.92
    ٢
    0.89
     paille
    0.88
     användas
    0.86
    accompag
    0.86
    برا
    0.84
    Warnings
    0.82
     nossa
    0.82
    cija
    0.82
    Activations Density 0.003%

    No Known Activations