© 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. 115837
    Prev
    Next
    INDEX
    Explanations

    package definitions

    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
     as
    -0.08
     all
    -0.06
     Run
    -0.06
     كافة
    -0.06
    ड़का
    -0.06
     supporting
    -0.06
     such
    -0.05
     this
    -0.05
     معد
    -0.05
    average
    -0.05
    POSITIVE LOGITS
     если
    0.07
     gdy
    0.07
     nếu
    0.07
     якщо
    0.07
    Très
    0.07
     paradox
    0.06
     Paradox
    0.06
    োনাম
    0.06
     automatisch
    0.06
     automáticamente
    0.06
    Activations Density 0.001%

    No Known Activations