© 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. 935
    Prev
    Next
    INDEX
    Explanations

    Nederland, voor museum

    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
     从
    2.11
     这个
    2.09
     这
    1.96
     一个
    1.94
    龙
    1.88
     通过
    1.88
     这里
    1.83
    比较
    1.80
    必须
    1.80
    此时
    1.77
    POSITIVE LOGITS
     voor
    2.24
     onder
    2.18
     zoals
    2.13
     verschillende
    2.13
     zelf
    2.08
     zonder
    2.08
     tussen
    2.07
     tijdens
    2.06
     mijn
    2.04
     nieuwe
    2.03
    Activations Density 0.056%

    No Known Activations