© 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. 128126
    Prev
    Next
    INDEX
    Explanations

    brand names and locations

    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
     kreatif
    -0.06
     входя
    -0.06
     unidade
    -0.06
     tricks
    -0.06
     रच
    -0.06
     скры
    -0.06
     défin
    -0.06
     Recharge
    -0.06
     التعريف
    -0.06
    Unit
    -0.06
    POSITIVE LOGITS
    大规模
    0.06
     reliable
    0.06
    reliable
    0.06
     большую
    0.06
    arov
    0.06
     considerable
    0.06
     Costa
    0.06
     studies
    0.05
     cercana
    0.05
     sizable
    0.05
    Activations Density 0.001%

    No Known Activations