© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49736
    Prev
    Next
    INDEX
    Explanations

    Caribbean geography

    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
     Chilean
    -0.98
     Mongolian
    -0.94
     Cambodian
    -0.88
     Tasmanian
    -0.87
     riverside
    -0.86
    Chile
    -0.85
    SALUD
    -0.84
     Korean
    -0.83
     australiano
    -0.82
    Canyon
    -0.82
    POSITIVE LOGITS
     Caribbean
    2.84
    Caribbean
    2.38
     caribbean
    1.95
     Barbados
    1.84
     Jamaica
    1.75
     Cari
    1.71
    cari
    1.71
     Antilles
    1.68
    Cari
    1.64
    Jamaica
    1.63
    Activations Density 0.075%

    No Known Activations