© 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. 127950
    Prev
    Next
    INDEX
    Explanations

    Q/A or headings

    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
     welchem
    -0.07
     Sleep
    -0.06
     завое
    -0.06
     удовольствием
    -0.06
    ॉक
    -0.06
     submer
    -0.06
     Gegensatz
    -0.06
     enjoys
    -0.06
     Bail
    -0.06
     погру
    -0.06
    POSITIVE LOGITS
     निश्चित
    0.07
     voldoende
    0.06
     startling
    0.06
     slur
    0.06
     systems
    0.06
     system
    0.06
    dirt
    0.06
    ज्ञानिक
    0.06
     схе
    0.06
    可怕
    0.05
    Activations Density 0.005%

    No Known Activations