© 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. 116125
    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
    etiti
    -0.07
     සමඟ
    -0.06
    스로
    -0.06
    Rq
    -0.06
    eqn
    -0.06
    গ
    -0.06
    并在
    -0.06
     deploying
    -0.06
     terrorists
    -0.06
    Jl
    -0.06
    POSITIVE LOGITS
    それぞれ
    0.06
     Throughout
    0.06
    ่อ
    0.06
     जागरूक
    0.06
    Throughout
    0.06
     Each
    0.06
     서로
    0.06
    筺
    0.06
     Coordinator
    0.06
     একে
    0.05
    Activations Density 0.006%

    No Known Activations