© 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. 128182
    Prev
    Next
    INDEX
    Explanations

    code comments or generated headers

    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
     сотрудник
    -0.06
     Khand
    -0.06
     বাসিন্দ
    -0.06
    移
    -0.06
     fret
    -0.06
     tyd
    -0.06
     பக்த
    -0.06
     फेड
    -0.06
     planned
    -0.06
     theoretically
    -0.06
    POSITIVE LOGITS
     and
    0.06
     অধিকাংশ
    0.06
     Insgesamt
    0.06
     các
    0.06
     međ
    0.06
     Overall
    0.06
    ’
    0.06
     inaugur
    0.05
    responseTime
    0.05
     ২০১৬
    0.05
    Activations Density 0.003%

    No Known Activations