© 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. 115916
    Prev
    Next
    INDEX
    Explanations

    PVP

    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
    âteaux
    -0.06
     reducing
    -0.06
     mining
    -0.06
     superfluous
    -0.06
    ociação
    -0.06
    শিক
    -0.06
     počíta
    -0.06
    ujudkan
    -0.06
    SAFETY
    -0.06
     savings
    -0.06
    POSITIVE LOGITS
     Maxine
    0.07
    交换
    0.06
     বাহিরে
    0.06
     default
    0.06
    appell
    0.06
     Dispute
    0.06
     물론
    0.06
    marie
    0.06
     vivre
    0.05
    xcs
    0.05
    Activations Density 0.001%

    No Known Activations