© 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. 115952
    Prev
    Next
    INDEX
    Explanations

    reason and logic

    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
    scientific
    -0.07
     scientific
    -0.06
     علم
    -0.06
     власть
    -0.06
     scientists
    -0.06
    Scientists
    -0.06
     нау
    -0.06
     सरकार
    -0.06
    ರವಾಗಿ
    -0.06
    government
    -0.06
    POSITIVE LOGITS
     reasoning
    0.07
     venezol
    0.06
     эмо
    0.06
     one
    0.06
     playoff
    0.06
    ১
    0.06
     rational
    0.05
    reason
    0.05
     الرحيم
    0.05
    🤧
    0.05
    Activations Density 0.009%

    No Known Activations