© 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. 120882
    Prev
    Next
    INDEX
    Explanations

    same-sex marriage and ceremonies

    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
     развития
    -0.07
     uncovering
    -0.07
    Development
    -0.07
     প্রত্যাখ্যান
    -0.06
     dezvolt
    -0.06
    リスク
    -0.06
     desarroll
    -0.06
     udvik
    -0.06
     development
    -0.06
     गोरख
    -0.06
    POSITIVE LOGITS
     when
    0.08
    เมื่อ
    0.07
    媲
    0.07
    unlike
    0.07
     když
    0.07
    when
    0.07
    When
    0.06
     WHEN
    0.06
     When
    0.06
     কর্মীদের
    0.06
    Activations Density 0.001%

    No Known Activations