© 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. 42597
    Prev
    Next
    INDEX
    Explanations

    establishments and institutions

    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
     are
    -1.38
    色んな
    -1.34
    我已经
    -1.30
    不得不说
    -1.27
     then
    -1.27
    你现在
    -1.27
    その時
    -1.23
    我现在
    -1.21
    わたしは
    -1.21
    未だ
    -1.20
    POSITIVE LOGITS
     unſ
    1.36
    ỗi
    1.34
     désolés
    1.27
    ableness
    1.27
    锱
    1.26
     centrum
    1.26
     Bursa
    1.25
     was
    1.23
     richtig
    1.23
    んでる
    1.23
    Activations Density 0.084%

    No Known Activations