© 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. 130148
    Prev
    Next
    INDEX
    Explanations

    feed fuel nourish

    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
     ក
    -0.06
    ✊
    -0.06
     ঘুম
    -0.06
     leichter
    -0.06
     or
    -0.06
    承受
    -0.06
     Lot
    -0.06
     sih
    -0.06
     Livestock
    -0.06
    基础上
    -0.06
    POSITIVE LOGITS
    Feeding
    0.06
     suggestive
    0.06
    Feed
    0.06
     sensación
    0.06
     nourishment
    0.06
     Necess
    0.06
    FEED
    0.06
     observational
    0.06
    feeding
    0.06
     feeding
    0.06
    Activations Density 0.049%

    No Known Activations