© 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. 56079
    Prev
    Next
    INDEX
    Explanations

    bolivian

    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
     Vancouver
    -0.83
    queira
    -0.81
     preescolar
    -0.79
     ம
    -0.77
    Vancouver
    -0.73
     offshore
    -0.72
    Carro
    -0.71
    swiper
    -0.71
     Offshore
    -0.71
     馬
    -0.71
    POSITIVE LOGITS
     Bolivia
    1.65
     Boli
    1.65
    Bolivia
    1.50
    Boli
    1.20
     boli
    0.95
     Siles
    0.94
     Montana
    0.94
     BOL
    0.93
     боли
    0.92
     coca
    0.91
    Activations Density 0.024%

    No Known Activations