© 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. 128253
    Prev
    Next
    INDEX
    Explanations

    cooking equipment and computational terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
     drugstore
    -0.07
    ट्रोल
    -0.07
     одино
    -0.07
     recipes
    -0.06
    BtnPanel
    -0.06
    皂
    -0.06
    Single
    -0.06
    个人
    -0.06
     دليل
    -0.06
    single
    -0.06
    POSITIVE LOGITS
    Sports
    0.06
     tomando
    0.06
    损失
    0.06
     أثناء
    0.06
     special
    0.06
     brane
    0.05
     முன்பு
    0.05
     during
    0.05
     PROBLEMS
    0.05
     durante
    0.05
    Activations Density 0.002%

    No Known Activations