© 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. 120903
    Prev
    Next
    INDEX
    Explanations

    patent titles and descriptions

    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
    Among
    -0.08
     amongst
    -0.06
    ியுடன்
    -0.06
     memorabilia
    -0.06
    ϑ
    -0.06
     weitere
    -0.06
     বিজ্ঞপ্তি
    -0.06
     beneficial
    -0.06
    他
    -0.06
     म्युच्युअल
    -0.06
    POSITIVE LOGITS
    intens
    0.06
     таким
    0.06
     arriba
    0.06
     already
    0.06
    ↵↵
    0.06
     embaixo
    0.06
     intuitively
    0.06
     patients
    0.06
    ikes
    0.05
    就知道
    0.05
    Activations Density 0.006%

    No Known Activations