© 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. 68348
    Prev
    Next
    INDEX
    Explanations

    Trend introduction

    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
    了一会儿
    -1.48
    同时也
    -1.34
     zey
    -1.33
     сегодняш
    -1.31
    鉏
    -1.30
     véhicules
    -1.29
    辿
    -1.27
    强行
    -1.23
     nästan
    -1.23
    Какие
    -1.23
    POSITIVE LOGITS
    ."
    1.59
     then
    1.56
    The
    1.38
    ",
    1.34
    ,"
    1.29
    ↵↵
    1.25
     advice
    1.24
    "
    1.23
     I
    1.23
    мый
    1.23
    Activations Density 0.001%

    No Known Activations