© 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. 116097
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     dvě
    -0.07
     two
    -0.07
    ២
    -0.06
     успеш
    -0.06
    Whoever
    -0.06
    dang
    -0.06
     TWO
    -0.06
     две
    -0.06
     oon
    -0.06
    这种情况
    -0.06
    POSITIVE LOGITS
    டன
    0.06
     hacia
    0.06
     craziness
    0.06
     carefully
    0.06
    様々な
    0.06
     virulence
    0.06
     variation
    0.06
     foray
    0.06
     tidak
    0.06
     possiamo
    0.06
    Activations Density 0.002%

    No Known Activations