© 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. 128133
    Prev
    Next
    INDEX
    Explanations

    topological insulators and defects

    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
    监听页面
    -0.06
     Museums
    -0.06
     Tenants
    -0.06
     pursuant
    -0.06
     tasting
    -0.06
     Regeneration
    -0.06
    ิท
    -0.06
     will
    -0.05
     immunization
    -0.05
     Muslim
    -0.05
    POSITIVE LOGITS
     macho
    0.06
     cả
    0.06
     đã
    0.06
     crap
    0.06
     của
    0.06
    高手
    0.06
    IBM
    0.06
     more
    0.06
    #############
    0.06
     更
    0.06
    Activations Density 0.001%

    No Known Activations