© 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. 120964
    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
    Negative Logits
    !
    -0.07
     these
    -0.07
     còn
    -0.06
     estas
    -0.06
    !,
    -0.06
    !',
    -0.06
     invece
    -0.06
     шумо
    -0.06
    ৯
    -0.06
     όσο
    -0.06
    POSITIVE LOGITS
     at
    0.06
    von
    0.06
     RandomForest
    0.06
     đi
    0.06
     sklearn
    0.06
    UnityEngine
    0.06
    ❶
    0.06
     nevoie
    0.06
     चांगले
    0.06
     UnityEngine
    0.06
    Activations Density 0.000%

    No Known Activations