© 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. 120902
    Prev
    Next
    INDEX
    Explanations

    court document identifiers and titles

    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
     true
    -0.06
     Volumen
    -0.06
    =$(
    -0.06
     the
    -0.06
     BETWEEN
    -0.05
    マ
    -0.05
     a
    -0.05
     volumen
    -0.05
     an
    -0.05
    true
    -0.05
    POSITIVE LOGITS
     కొన్ని
    0.07
     unele
    0.07
     வண்ணப்பூ
    0.06
     পশ্চিমবঙ্গের
    0.06
     mitä
    0.06
     ممكن
    0.06
     എല്ലാ
    0.06
     hesitant
    0.06
     হতাশ
    0.06
     बदमाशों
    0.06
    Activations Density 0.003%

    No Known Activations