© 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. 120718
    Prev
    Next
    INDEX
    Explanations

    Supported by

    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
    Not in Any Lists

    No Comments

    Negative Logits
     svog
    -0.07
     التج
    -0.06
     اجر
    -0.06
     operativos
    -0.06
     outwards
    -0.06
    BASE
    -0.06
     comedic
    -0.06
     perdita
    -0.06
     свого
    -0.06
     tiap
    -0.06
    POSITIVE LOGITS
     múltiples
    0.07
     proporcionan
    0.06
     Extra
    0.06
    はありません
    0.06
     большо
    0.06
     statewide
    0.06
     obtener
    0.06
     deliver
    0.06
     overweight
    0.05
     devise
    0.05
    Activations Density 0.001%

    No Known Activations