© 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. 59453
    Prev
    Next
    INDEX
    Explanations

    technical specifications

    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
     pesky
    -1.49
     يوجد
    -1.49
     yine
    -1.40
     disorderly
    -1.35
     strangest
    -1.33
     basit
    -1.30
     автомобилей
    -1.29
     upheaval
    -1.28
     laterales
    -1.28
     İ
    -1.28
    POSITIVE LOGITS
     матч
    1.38
     MATHEMAT
    1.37
     аппети
    1.34
     ohr
    1.34
    ּוֹ
    1.34
     persönlich
    1.32
     YOGA
    1.32
     ACKNOWLEDGMENTS
    1.29
     dortmund
    1.27
    dirond
    1.26
    Activations Density 0.011%

    No Known Activations