© 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. 93332
    Prev
    Next
    INDEX
    Explanations

    mathematical and code expressions

    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
    是什么
    -0.91
    为空
    -0.90
     idi
    -0.90
     ALAN
    -0.89
     reis
    -0.88
     sinn
    -0.88
     deter
    -0.87
    訥
    -0.87
     berg
    -0.86
     comunión
    -0.85
    POSITIVE LOGITS
    //{
    0.95
    🏺
    0.91
     membayar
    0.90
    сию
    0.89
     нержа
    0.88
     қара
    0.88
     biztons
    0.88
     parseFrom
    0.88
     pouvoirs
    0.87
    に行ってきました
    0.87
    Activations Density 0.033%

    No Known Activations