© 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. 115859
    Prev
    Next
    INDEX
    Explanations

    code imports and declarations

    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
     or
    -0.07
    technology
    -0.07
     teknologi
    -0.07
     tecnología
    -0.06
     technology
    -0.06
     tecnológicas
    -0.06
    前の
    -0.06
     इसमें
    -0.06
     filosof
    -0.06
     alebo
    -0.06
    POSITIVE LOGITS
    ရာ
    0.06
     Assn
    0.06
     obtenue
    0.05
     някои
    0.05
    fred
    0.05
     نتيجة
    0.05
     alcuni
    0.05
     Ein
    0.05
     تانيه
    0.05
     දි
    0.05
    Activations Density 0.001%

    No Known Activations