© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128343
    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
     bảy
    -0.06
     novos
    -0.06
     copertura
    -0.06
    🍴
    -0.06
     अपन
    -0.06
     सहारा
    -0.06
     reais
    -0.06
     новое
    -0.06
     dictatorship
    -0.06
    買取
    -0.06
    POSITIVE LOGITS
     RELATED
    0.06
     použív
    0.06
     efficiencies
    0.06
    を利用
    0.06
     použí
    0.06
    Across
    0.06
     metabolic
    0.06
    <0xC2>
    0.06
    promoting
    0.06
     lineages
    0.06
    Activations Density 0.000%

    No Known Activations