© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48709
    Prev
    Next
    INDEX
    Explanations

    Hungary Hungarian Budapest Magyar

    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
     jöv
    -1.11
     gyerek
    -1.09
     zöld
    -1.05
     gyermek
    -1.03
     város
    -0.98
     női
    -0.98
     település
    -0.96
     csalá
    -0.96
     szép
    -0.95
     verseny
    -0.91
    POSITIVE LOGITS
     Hungarian
    2.03
     Hungary
    1.82
    Hungarian
    1.74
     Budapest
    1.66
    Hungary
    1.53
    Budapest
    1.29
     Magyar
    1.25
     paprika
    1.16
     Nagy
    1.11
     Hongrie
    1.11
    Activations Density 0.068%

    No Known Activations