© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120990
    Prev
    Next
    INDEX
    Explanations

    administrative divisions

    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
    Negative Logits
     трех
    -0.07
     மூன்று
    -0.07
     पांच
    -0.06
     трёх
    -0.06
     five
    -0.06
     розді
    -0.06
    हाला
    -0.06
     fifth
    -0.06
     الرابع
    -0.06
    five
    -0.06
    POSITIVE LOGITS
     local
    0.06
     ڕ
    0.06
     זה
    0.06
     स्थान
    0.06
     physical
    0.05
     なら
    0.05
     localized
    0.05
    RR
    0.05
    mselves
    0.05
    攫
    0.05
    Activations Density 0.017%

    No Known Activations