© 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. 39170
    Prev
    Next
    INDEX
    Explanations

    as of March

    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
     was
    -1.80
     as
    -1.60
     one
    -1.52
    ."
    -1.43
    }
    -1.36
     in
    -1.34
     still
    -1.34
     into
    -1.28
     set
    -1.27
     sent
    -1.27
    POSITIVE LOGITS
     регулярно
    1.68
    ◆◆
    1.67
    حتی
    1.65
    谖
    1.64
    são
    1.64
    ↑↑↑
    1.62
    Ahol
    1.61
    här
    1.61
    ཫ
    1.60
    Forrás
    1.57
    Activations Density 0.023%

    No Known Activations