© 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. 41562
    Prev
    Next
    INDEX
    Explanations

    Chinese/Japanese characters

    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
     The
    -2.47
     {
    -2.47
     \
    -2.39
     With
    -2.11
     esos
    -2.09
    й
    -2.08
    /
    -2.08
    t
    -2.02
    ي
    -2.02
     BEFORE
    -1.95
    POSITIVE LOGITS
    gucig
    2.59
    谵
    2.55
    ᯅ
    2.44
    这么多
    2.42
    玙
    2.36
    慙
    2.33
    謦
    2.14
    숑
    2.13
    我们就
    2.13
     笑顔
    2.09
    Activations Density 0.000%

    No Known Activations