© 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. 115998
    Prev
    Next
    INDEX
    Explanations

    central control or distributed systems

    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
     configured
    -0.07
     ज़्यादा
    -0.06
     considera
    -0.06
     get
    -0.06
     varia
    -0.06
    ন্যাশনাল
    -0.06
     appliquée
    -0.06
    を使用して
    -0.06
    امج
    -0.06
     oblik
    -0.06
    POSITIVE LOGITS
    sers
    0.06
    在这个
    0.06
    README
    0.06
    atanam
    0.06
     reeling
    0.06
     OLED
    0.06
    ிறார்கள்
    0.05
     omitted
    0.05
     vertebra
    0.05
     warehousing
    0.05
    Activations Density 0.004%

    No Known Activations