© 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. 34-GEMMASCOPE-RES-131K
    7. 82510
    Prev
    Next
    INDEX
    Explanations

    Regional anesthesia or SWIG

    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
     coaxial
    -0.77
     presença
    -0.77
     transición
    -0.77
    Procedures
    -0.75
     чолові
    -0.74
    Kapp
    -0.71
     Runde
    -0.70
    ڵ
    -0.69
     cuenca
    -0.69
    生气
    -0.68
    POSITIVE LOGITS
    SWIG
    0.93
    antuan
    0.91
     SWIG
    0.86
    轼
    0.85
    Python
    0.84
    瘧
    0.83
    ｀*)
    0.81
     ждать
    0.81
    Scottish
    0.81
     *$
    0.81
    Activations Density 0.003%

    No Known Activations