© 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. 128019
    Prev
    Next
    INDEX
    Explanations

    error messages and warnings

    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
     днем
    -0.07
     Argument
    -0.06
    relevant
    -0.06
     зокрема
    -0.05
     allgeme
    -0.05
     précise
    -0.05
     balloons
    -0.05
     مصروف
    -0.05
     glial
    -0.05
     items
    -0.05
    POSITIVE LOGITS
     douze
    0.07
    जेश
    0.07
     разных
    0.07
     unterschied
    0.06
     zwölf
    0.06
     separator
    0.06
     रखती
    0.06
     Hel
    0.06
     няколко
    0.06
     diferentes
    0.06
    Activations Density 0.001%

    No Known Activations