© 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. 128152
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Q:"

    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
     also
    -0.07
     रोपवे
    -0.06
     has
    -0.06
     ஈடுபட்டு
    -0.06
     وير
    -0.06
     incredibly
    -0.06
     außerdem
    -0.06
     دو
    -0.06
     moreover
    -0.06
     knot
    -0.06
    POSITIVE LOGITS
     って
    0.07
     federally
    0.06
     मस्
    0.06
    Ты
    0.06
     Existing
    0.06
     intenta
    0.06
    たとえば
    0.06
    膿
    0.06
    렇게
    0.06
     sarebbe
    0.06
    Activations Density 0.003%

    No Known Activations