© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 47850
    Prev
    Next
    INDEX
    Explanations

    button click events

    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
     nabíz
    -1.00
    always
    -0.94
    labelControl
    -0.93
     oorspron
    -0.91
     odstran
    -0.90
    这几
    -0.89
     použití
    -0.89
    another
    -0.89
     krach
    -0.85
     لئے
    -0.84
    POSITIVE LOGITS
     on
    1.42
     only
    1.13
     button
    1.03
     btn
    1.01
     Form
    1.01
     On
    0.93
     Button
    0.89
     MainWindow
    0.89
    On
    0.88
     endast
    0.87
    Activations Density 0.007%

    No Known Activations