© 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. 120933
    Prev
    Next
    INDEX
    Explanations

    favorite quotation, Nick Pickard, 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
     fondamentale
    -0.06
     важней
    -0.06
     accordance
    -0.06
     verdadera
    -0.06
     belangrijke
    -0.06
     fondamentali
    -0.06
     استح
    -0.06
     vastly
    -0.06
    roku
    -0.05
     полноцен
    -0.05
    POSITIVE LOGITS
     Xuân
    0.06
    ंसाठी
    0.06
     avec
    0.06
     edición
    0.06
    ować
    0.06
    Frozen
    0.06
     już
    0.06
    意识到
    0.06
     prototyping
    0.06
     būti
    0.06
    Activations Density 0.001%

    No Known Activations