© 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. 640
    Prev
    Next
    INDEX
    Explanations

    Norwegian and Swedish pronouns

    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
     достаточно
    1.34
     сохра
    1.23
     часто
    1.21
     خواه
    1.14
    Ə
    1.13
     сдела
    1.13
     toxic
    1.12
     toda
    1.11
    變
    1.11
     mostly
    1.10
    POSITIVE LOGITS
     gjennom
    2.13
     kjø
    2.10
     utvik
    2.01
     høy
    1.94
     på
    1.93
     uten
    1.90
     fikk
    1.89
     mellom
    1.87
     gjør
    1.87
     også
    1.86
    Activations Density 0.028%

    No Known Activations