© 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. 120798
    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
     bardzo
    -0.06
     매우
    -0.06
     পার্ক
    -0.06
    ├──
    -0.06
     their
    -0.06
    ඡ
    -0.06
     사진
    -0.06
     his
    -0.06
    遭受
    -0.05
    Suitable
    -0.05
    POSITIVE LOGITS
    Other
    0.07
    ativo
    0.06
     statewide
    0.06
    ativa
    0.06
    这么
    0.06
    ativos
    0.05
    原始内容存档于
    0.05
     자체가
    0.05
     abreast
    0.05
    ATIVA
    0.05
    Activations Density 0.000%

    No Known Activations