© 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. 115861
    Prev
    Next
    INDEX
    Explanations

    code block delimiters and keywords

    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
    精力
    -0.06
     pratic
    -0.06
     kya
    -0.06
    ↵↵
    -0.06
     confines
    -0.06
     എഴു
    -0.06
     London
    -0.05
    也
    -0.05
     confined
    -0.05
     gentile
    -0.05
    POSITIVE LOGITS
     রাখার
    0.06
    Quote
    0.06
     tipo
    0.06
     kiểu
    0.06
     siempre
    0.06
    ＜
    0.06
     बाहरी
    0.06
     지금까지
    0.06
     همیشه
    0.06
    Waiting
    0.06
    Activations Density 0.001%

    No Known Activations