© 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. 119230
    Prev
    Next
    INDEX
    Explanations

    economic jurisdictions

    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
    safety
    -0.06
     Warfare
    -0.06
    পূর্ব
    -0.06
     রহস্য
    -0.06
     ejemplo
    -0.06
    imagery
    -0.06
     teleport
    -0.05
     hao
    -0.05
     ಗಾ
    -0.05
     上
    -0.05
    POSITIVE LOGITS
     οικονομ
    0.06
    經濟
    0.06
    经济
    0.06
     financial
    0.06
     alcune
    0.06
     ECON
    0.06
     económica
    0.06
    제로
    0.06
     économiques
    0.06
    arse
    0.06
    Activations Density 0.002%

    No Known Activations