© 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. 115856
    Prev
    Next
    INDEX
    Explanations

    African presidents, Russia, terminal, elle

    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
    하여
    -0.06
    🦓
    -0.06
     будь
    -0.06
     inhalation
    -0.06
    🦈
    -0.06
    ฬา
    -0.06
    瀏
    -0.06
     cerebral
    -0.06
    Racing
    -0.06
     Blaze
    -0.06
    POSITIVE LOGITS
     Installer
    0.07
    远程
    0.06
     remittances
    0.06
    '',
    0.06
    indicate
    0.06
    日程
    0.06
     montaje
    0.06
     telep
    0.06
     jusqu
    0.06
     Οι
    0.06
    Activations Density 0.002%

    No Known Activations