© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117894
    Prev
    Next
    INDEX
    Explanations

    Islamic Republic

    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
    就连
    -0.06
     mentality
    -0.06
     surtout
    -0.06
     specified
    -0.06
     tiež
    -0.06
    ワゴン
    -0.06
     salle
    -0.06
     även
    -0.06
     LANGUAGE
    -0.06
     валю
    -0.06
    POSITIVE LOGITS
     اسم
    0.07
     would
    0.06
     concentrated
    0.06
     edges
    0.06
     به‌عنوان
    0.06
     ಹುಡು
    0.06
     zouden
    0.06
     empl
    0.06
     لوبې
    0.06
     herv
    0.06
    Activations Density 0.002%

    No Known Activations