© 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. 34-GEMMASCOPE-RES-131K
    7. 78130
    Prev
    Next
    INDEX
    Explanations

    sections and endpoints

    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
     â
    -0.96
     ener
    -0.96
     Ajouter
    -0.95
     ì
    -0.93
     Ã
    -0.90
     ٢
    -0.90
     
    -0.88
    付いて
    -0.88
    ┬
    -0.88
     adecu
    -0.87
    POSITIVE LOGITS
    <eos>
    1.50
     Conclusion
    1.42
    Conclusion
    1.32
    <h2>
    1.23
     CONCLUSION
    1.08
    CHAPTER
    1.07
    <h1>
    1.07
     What
    1.06
     CHAPTER
    1.04
     How
    1.02
    Activations Density 0.114%

    No Known Activations