© 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. 116047
    Prev
    Next
    INDEX
    Explanations

    opening

    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
     vomiting
    -0.06
    ່ງ
    -0.06
     encontr
    -0.06
    গীর
    -0.06
    exempl
    -0.06
    辐
    -0.06
    expect
    -0.06
    隙
    -0.06
     expect
    -0.06
     найден
    -0.06
    POSITIVE LOGITS
     trabalhar
    0.07
     താര
    0.07
     ekonomi
    0.07
     florist
    0.06
     පමණ
    0.06
     northeast
    0.06
    insured
    0.06
    returned
    0.06
     इस
    0.06
    %!
    0.06
    Activations Density 0.011%

    No Known Activations