© 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. 128017
    Prev
    Next
    INDEX
    Explanations

    # Math

    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
     lacking
    -0.07
     সাপোর্ট
    -0.06
     njih
    -0.06
    $-\
    -0.06
    folds
    -0.06
     أفضل
    -0.06
     dealing
    -0.06
     গিয়েছে
    -0.06
    咱们
    -0.06
     अडचणी
    -0.06
    POSITIVE LOGITS
     supaya
    0.07
    imary
    0.06
     этом
    0.06
     তখনই
    0.06
     ಮೂಲಕ
    0.06
     avrebbe
    0.06
    കൂ
    0.06
     Jing
    0.06
     alph
    0.06
    까지
    0.06
    Activations Density 0.001%

    No Known Activations