© 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. 119074
    Prev
    Next
    INDEX
    Explanations

    Qt framework and versions

    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
     maroca
    -0.77
     golfers
    -0.74
     manor
    -0.74
     fogo
    -0.74
     teeth
    -0.71
    些
    -0.71
    maphore
    -0.71
    eml
    -0.69
    нями
    -0.69
    实行
    -0.69
    POSITIVE LOGITS
    QT
    0.85
     QtWidgets
    0.84
     Qt
    0.81
    oblotting
    0.79
     QT
    0.75
    IOL
    0.75
     semula
    0.72
    ⎡
    0.72
    assistant
    0.71
     stoves
    0.71
    Activations Density 0.068%

    No Known Activations