© 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. 34-GEMMASCOPE-RES-131K
    7. 38636
    Prev
    Next
    INDEX
    Explanations

    static final

    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_34/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
     why
    -1.09
    應該是
    -1.07
     them
    -1.05
    Donde
    -1.04
    inverno
    -1.03
     矢量
    -1.01
    animity
    -1.00
     包装
    -1.00
     яке
    -0.99
     moindre
    -0.98
    POSITIVE LOGITS
     final
    2.75
    final
    2.45
     readonly
    1.52
     volatile
    1.48
     the
    1.45
    volatile
    1.38
     finally
    1.34
     FINAL
    1.32
    Finally
    1.31
    最后
    1.23
    Activations Density 0.005%

    No Known Activations