© 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. 98226
    Prev
    Next
    INDEX
    Explanations

    switch or switching

    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
    jectory
    -0.78
    粼
    -0.78
    gevens
    -0.71
    Dragged
    -0.71
     końca
    -0.70
     planters
    -0.69
    ğimiz
    -0.69
    bunga
    -0.68
    鮒
    -0.68
     aDecoder
    -0.68
    POSITIVE LOGITS
     switch
    3.50
     switching
    3.45
    switch
    3.09
     switches
    2.97
     Switching
    2.95
     swit
    2.95
    Switch
    2.89
    切换
    2.83
    Switching
    2.81
    switching
    2.80
    Activations Density 0.119%

    No Known Activations