© 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. 116016
    Prev
    Next
    INDEX
    Explanations

    programming code structure

    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
     সহিংস
    -0.07
     respective
    -0.06
     excitedly
    -0.06
     JOHN
    -0.06
     undeniably
    -0.06
     yalnızca
    -0.06
     JOHNSON
    -0.06
     hims
    -0.06
    JOHN
    -0.06
    そんな
    -0.06
    POSITIVE LOGITS
     as
    0.07
     зимо
    0.06
     a
    0.06
     о
    0.06
     there
    0.06
     размеры
    0.06
     நீதிமன்ற
    0.06
     erfüllen
    0.06
     बनाती
    0.06
     참석
    0.06
    Activations Density 0.005%

    No Known Activations