© 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. 121018
    Prev
    Next
    INDEX
    Explanations

    contrast enhancement

    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
     first
    -0.06
     still
    -0.06
     начало
    -0.06
    Mediterr
    -0.06
     digitally
    -0.06
     rapidamente
    -0.06
     início
    -0.06
     อย่าง
    -0.06
     last
    -0.06
     Digital
    -0.06
    POSITIVE LOGITS
    लॉक
    0.06
     అత్య
    0.06
    Airport
    0.06
     consensus
    0.06
    airport
    0.06
    tonne
    0.06
     Амери
    0.05
     미국
    0.05
     lesson
    0.05
     మీ
    0.05
    Activations Density 0.002%

    No Known Activations