© 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. 128049
    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
    全部
    -0.07
    这个人
    -0.07
    所有
    -0.06
     necesarias
    -0.06
    そんな
    -0.06
    quel
    -0.06
    ⑥
    -0.05
     전부
    -0.05
     上
    -0.05
     menurut
    -0.05
    POSITIVE LOGITS
     în
    0.07
     While
    0.07
     the
    0.06
     posiblemente
    0.06
     with
    0.06
     in
    0.06
    を知
    0.06
    While
    0.06
     Separate
    0.06
     Jalis
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.