© 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. 11874
    Prev
    Next
    INDEX
    Explanations

    I suspect

    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
     we
    -1.50
    ޗ
    -1.38
    >();
    -1.35
     provenant
    -1.35
     précédemment
    -1.30
     Presumably
    -1.29
    ętr
    -1.28
    
    -1.27
    ！”
    -1.27
    miş
    -1.27
    POSITIVE LOGITS
     of
    1.68
    今後も
    1.50
    "
    1.32
    営業時間
    1.31
    つづく
    1.25
    能让
    1.24
    これからも
    1.24
     vienas
    1.23
     ausgezeichnet
    1.23
    脍
    1.21
    Activations Density 0.041%

    No Known Activations