© 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. 116081
    Prev
    Next
    INDEX
    Explanations

    time or duration

    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
    意识
    -0.05
     superimposed
    -0.05
    irical
    -0.05
     ສະ
    -0.05
     passos
    -0.05
    ŗ
    -0.05
    上了
    -0.05
    意識
    -0.05
     modeled
    -0.05
    パリ
    -0.05
    POSITIVE LOGITS
     như
    0.08
    往往
    0.07
     comme
    0.07
     como
    0.07
     لل
    0.07
     dianggap
    0.07
     peuvent
    0.07
     преподава
    0.07
     podem
    0.07
     можуть
    0.07
    Activations Density 0.001%

    No Known Activations