© 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. 128137
    Prev
    Next
    INDEX
    Explanations

    website and mentions

    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
     ermöglicht
    -0.07
     इच्छ
    -0.07
     inéd
    -0.06
    ->"
    -0.06
     jeder
    -0.06
     तुम्हारे
    -0.06
     costume
    -0.06
     kostet
    -0.06
    こんな
    -0.06
     fotografia
    -0.06
    POSITIVE LOGITS
     its
    0.07
     stated
    0.07
    ホームページ
    0.07
     their
    0.07
     appears
    0.07
     أنها
    0.07
     website
    0.06
     فهي
    0.06
     appear
    0.06
     их
    0.06
    Activations Density 0.005%

    No Known Activations