© 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. 107591
    Prev
    Next
    INDEX
    Explanations

    New Zealand places and people

    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
    ၀
    -0.80
    会議
    -0.75
    alibaba
    -0.71
     uma
    -0.71
    𝙲
    -0.71
     cortada
    -0.70
     focused
    -0.70
     Maryland
    -0.70
     nilai
    -0.69
     że
    -0.68
    POSITIVE LOGITS
     NZ
    2.03
     Zealand
    1.77
     Kiwi
    1.75
    NZ
    1.75
     Australia
    1.69
     kiwi
    1.69
     Auckland
    1.61
     Maori
    1.52
    Kiwi
    1.51
     نيوز
    1.49
    Activations Density 0.055%

    No Known Activations