© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 6691
    Prev
    Next
    INDEX
    Explanations

    Dutch language queries asking how to do things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     이전
    1.18
     무
    1.16
    과
    1.13
     마
    1.02
     신
    1.01
     유지
    1.01
     아무
    1.01
    마다
    1.00
     효
    1.00
    文本
    0.99
    POSITIVE LOGITS
    Een
    1.90
    Voor
    1.85
    Dutch
    1.78
     onder
    1.65
     Dutch
    1.65
    Amsterdam
    1.58
    Neder
    1.58
     gaat
    1.57
     gebruik
    1.57
    Waar
    1.56
    Activations Density 0.011%

    No Known Activations