© 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. 70270
    Prev
    Next
    INDEX
    Explanations

    migration and moving

    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
    7
    -0.94
     Montevideo
    -0.90
    8
    -0.87
    ⅕
    -0.86
    Skal
    -0.81
    2
    -0.80
    invoices
    -0.79
     nhiệm
    -0.79
    Familie
    -0.79
     trinken
    -0.79
    POSITIVE LOGITS
     Migration
    2.00
     Mig
    1.94
     mig
    1.91
    Mig
    1.79
     migration
    1.77
     migrant
    1.73
    Migration
    1.71
     migrating
    1.64
    mig
    1.61
    migration
    1.51
    Activations Density 0.023%

    No Known Activations