© 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. 116197
    Prev
    Next
    INDEX
    Explanations

    Formula 1 drivers

    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
     Raw
    -0.07
     raw
    -0.06
    Raw
    -0.06
     production
    -0.06
     official
    -0.06
    生産
    -0.06
    生
    -0.06
    生產
    -0.06
    production
    -0.06
     производ
    -0.06
    POSITIVE LOGITS
     teamwork
    0.08
     knocked
    0.07
     synergy
    0.06
     Hendrik
    0.06
     কম্পিউ
    0.06
     synerg
    0.06
     mål
    0.06
     সৌর
    0.06
     asleep
    0.06
     vosotros
    0.06
    Activations Density 0.005%

    No Known Activations