© 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. 120946
    Prev
    Next
    INDEX
    Explanations

    traditional, unchanged, or nomadic lifestyles

    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
     mainstream
    -0.06
    embalikan
    -0.06
     כמו
    -0.06
    ilerden
    -0.06
     INSTIT
    -0.06
     هدف
    -0.06
     초기
    -0.06
    原料
    -0.06
    机构
    -0.06
     क्रिस्ट
    -0.06
    POSITIVE LOGITS
    Despite
    0.07
    เพียง
    0.07
     Despite
    0.07
     स्वातंत्र
    0.06
     despite
    0.06
     कई
    0.06
     siguiendo
    0.06
     ಹಲವಾರು
    0.06
     awesome
    0.06
     splendid
    0.06
    Activations Density 0.008%

    No Known Activations