© 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. 120925
    Prev
    Next
    INDEX
    Explanations

    urls after brackets

    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
     four
    -0.06
     無
    -0.06
     pentru
    -0.06
     با
    -0.06
     high
    -0.06
     limited
    -0.06
     不
    -0.06
     بدون
    -0.05
     approximate
    -0.05
    used
    -0.05
    POSITIVE LOGITS
    特别是
    0.07
     speziell
    0.07
     picky
    0.06
     particulier
    0.06
     videos
    0.06
    新款
    0.06
     genuinely
    0.06
    พิเศษ
    0.06
     réel
    0.06
    新能源
    0.06
    Activations Density 0.002%

    No Known Activations