© 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. 10-GEMMASCOPE-RES-131K
    7. 3880
    Prev
    Next
    INDEX
    Explanations

    plural endings and transliteration

    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_10/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
    ↑↑↑</
    -2.30
    欵
    -2.05
    縂
    -1.92
     ikke
    -1.89
    豋
    -1.87
     テラス
    -1.83
    ၟ
    -1.80
    ¹.
    -1.78
     пароль
    -1.76
     zulassen
    -1.75
    POSITIVE LOGITS
     are
    2.14
    蛲
    2.02
     It
    1.88
    
    1.83
     dà
    1.81
    蟥
    1.81
     و
    1.77
    桫
    1.75
     มี
    1.70
     тату
    1.69
    Activations Density 0.174%

    No Known Activations