© 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. 120732
    Prev
    Next
    INDEX
    Explanations

    feminist women's issues

    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
     często
    -0.07
     your
    -0.07
     voluntad
    -0.06
    Número
    -0.06
     their
    -0.06
     COMPUTER
    -0.06
     spouse
    -0.06
     비율
    -0.06
     त्यांचे
    -0.06
    他們
    -0.06
    POSITIVE LOGITS
     state
    0.07
     new
    0.06
     exhilar
    0.06
     paid
    0.05
     разбира
    0.05
    ыска
    0.05
     designed
    0.05
    ❃
    0.05
     특별
    0.05
    mult
    0.05
    Activations Density 0.024%

    No Known Activations