© 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. 110858
    Prev
    Next
    INDEX
    Explanations

    United States travel and visas

    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
    Bern
    -0.85
     Columb
    -0.80
    Efter
    -0.79
    PROPERTY
    -0.78
    UIControlState
    -0.77
    贛
    -0.77
    Prices
    -0.76
    Hybrid
    -0.76
     cafeteria
    -0.75
    IPCC
    -0.75
    POSITIVE LOGITS
     travel
    1.55
     ban
    1.33
     Travel
    1.28
    travel
    1.25
    Travel
    1.10
     travelers
    1.09
    immigration
    0.97
     version
    0.94
    TRAVEL
    0.94
     visa
    0.94
    Activations Density 0.014%

    No Known Activations