© 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. 90302
    Prev
    Next
    INDEX
    Explanations

    context 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
     Viz
    -0.72
     Honeymoon
    -0.71
     المسي
    -0.71
     nonce
    -0.69
     biến
    -0.69
     Hann
    -0.68
     skirt
    -0.68
    ,$_
    -0.67
    pren
    -0.66
     influencia
    -0.66
    POSITIVE LOGITS
     switching
    1.91
     Switching
    1.84
    switching
    1.74
    Switching
    1.73
    切换
    1.68
     switch
    1.61
     context
    1.59
    Switch
    1.55
     Switch
    1.55
     SWITCH
    1.46
    Activations Density 0.067%

    No Known Activations