© 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. 61273
    Prev
    Next
    INDEX
    Explanations

    managing various entities

    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
     longtime
    -1.84
     It
    -1.75
    做法
    -1.73
     method
    -1.60
     französ
    -1.57
    方法
    -1.57
     gewesen
    -1.55
    3
    -1.55
    -
    -1.52
     genannt
    -1.49
    POSITIVE LOGITS
    Цита
    1.90
    Whether
    1.80
    茘
    1.79
    曁
    1.65
    Diese
    1.63
    Примеча
    1.55
    Зри
    1.52
     taban
    1.50
    ㌧
    1.49
    Итог
    1.48
    Activations Density 0.037%

    No Known Activations