© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74795
    Prev
    Next
    INDEX
    Explanations

    water, mud, and debris

    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
    訫
    -1.48
    这些
    -1.38
     também
    -1.36
    iſter
    -1.36
     ouverts
    -1.34
    一个
    -1.32
     sebuah
    -1.31
     of
    -1.30
     seorang
    -1.28
     però
    -1.27
    POSITIVE LOGITS
     from
    1.60
     other
    1.48
     آن‌ها
    1.27
     previous
    1.24
    باء
    1.23
     zahlreiche
    1.23
    回到了
    1.22
     everything
    1.21
     its
    1.20
    コミュ
    1.20
    Activations Density 0.058%

    No Known Activations