© 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. 120952
    Prev
    Next
    INDEX
    Explanations

    docker commands and files

    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
     Ernesto
    -0.06
    journ
    -0.06
     caret
    -0.06
     esperamos
    -0.06
     যুবক
    -0.06
     we
    -0.06
     selecion
    -0.06
     boasting
    -0.06
     ausgewählt
    -0.06
     smak
    -0.06
    POSITIVE LOGITS
     gde
    0.07
     её
    0.07
    她的
    0.07
    痔
    0.06
     dave
    0.06
     samot
    0.06
    ನ್ಯ
    0.06
     буквально
    0.06
    genius
    0.06
     Armor
    0.06
    Activations Density 0.011%

    No Known Activations