© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119486
    Prev
    Next
    INDEX
    Explanations

    Swedish and Norwegian words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    札幌
    -0.06
     facility
    -0.06
     کړ
    -0.06
     наиболь
    -0.06
     લગભગ
    -0.06
     Every
    -0.06
    ursed
    -0.06
     earliest
    -0.06
    issenschaft
    -0.06
     специальные
    -0.05
    POSITIVE LOGITS
    ைகளின்
    0.06
    ogène
    0.06
     pochod
    0.06
     Houston
    0.06
    staaten
    0.06
    我和
    0.05
    adiator
    0.05
     podpis
    0.05
     Instruments
    0.05
    ！（
    0.05
    Activations Density 0.119%

    No Known Activations