© 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. 596
    Prev
    Next
    INDEX
    Explanations

    Australian geographical places

    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
    小山
    -0.79
     Seattle
    -0.77
     امام
    -0.75
     Puget
    -0.73
     obreros
    -0.71
    可能です
    -0.71
    Laurel
    -0.70
     importers
    -0.70
    ills
    -0.69
    envol
    -0.69
    POSITIVE LOGITS
     desert
    1.48
     Outback
    1.34
    desert
    1.30
     deserts
    1.20
     Desert
    1.20
     outback
    1.20
     camels
    1.19
    Desert
    1.17
    沙漠
    1.00
     Rajasthan
    0.99
    Activations Density 0.022%

    No Known Activations