© 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. 115994
    Prev
    Next
    INDEX
    Explanations

    Recent developments specification World Job Basket

    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
     geothermal
    -0.07
     soort
    -0.06
     thermodynamic
    -0.06
     हाद
    -0.06
     typedef
    -0.06
     similaire
    -0.06
     asymptotics
    -0.06
     نوع
    -0.06
    ayant
    -0.06
     similares
    -0.06
    POSITIVE LOGITS
     pathways
    0.06
     адво
    0.06
     attravers
    0.06
     चैनल
    0.06
     Pathways
    0.06
     Interstate
    0.06
    ་་
    0.06
    ̜
    0.06
     vertebrate
    0.06
    Channel
    0.06
    Activations Density 0.016%

    No Known Activations