© 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. 120860
    Prev
    Next
    INDEX
    Explanations

    using an unsupported browser

    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
     굉장히
    -0.07
     bardzo
    -0.07
     çok
    -0.07
     বিপুল
    -0.07
     여러
    -0.07
     très
    -0.07
     allerlei
    -0.06
     large
    -0.06
    없
    -0.06
     كثير
    -0.06
    POSITIVE LOGITS
    current
    0.06
     until
    0.06
    That
    0.06
     quartet
    0.05
    \:
    0.05
    4
    0.05
    日まで
    0.05
    liegt
    0.05
     হওয়ার
    0.05
    פן
    0.05
    Activations Density 0.002%

    No Known Activations