© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 64
    Prev
    Next
    INDEX
    Explanations

    Scandinavian language elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Если
    0.66
    Э
    0.62
     Pentru
    0.61
     Для
    0.60
     возле
    0.60
     Это
    0.60
     Với
    0.60
    İ
    0.58
     Эта
    0.58
     Пере
    0.58
    POSITIVE LOGITS
     større
    0.50
     den
    0.48
     hoved
    0.48
     små
    0.46
     denne
    0.45
     flere
    0.44
     det
    0.44
     verdens
    0.43
     mennes
    0.43
     både
    0.43
    Activations Density 0.013%

    No Known Activations