© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67338
    Prev
    Next
    INDEX
    Explanations

    codes and modules

    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
    utzung
    -1.26
    Zitat
    -1.20
    朧
    -1.18
     veulent
    -1.18
     récente
    -1.16
    訁
    -1.15
    婚礼
    -1.15
    SOLUTION
    -1.14
     Verpflich
    -1.14
     имеют
    -1.13
    POSITIVE LOGITS
     nine
    1.37
     that
    1.36
    出來的
    1.30
     four
    1.20
    協助
    1.18
    
    1.18
     plenty
    1.17
     one
    1.16
    0
    1.16
    st
    1.15
    Activations Density 0.031%

    No Known Activations