© 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. 118029
    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
    在這裡
    -0.06
    inicio
    -0.06
     allí
    -0.06
    trong
    -0.06
     tqdm
    -0.06
     там
    -0.06
     aquí
    -0.05
     udrž
    -0.05
     polynomial
    -0.05
     ainsi
    -0.05
    POSITIVE LOGITS
     Ova
    0.06
     выигра
    0.06
    េះ
    0.06
     परवानगी
    0.06
     salto
    0.06
     পরিকল্পিত
    0.06
    ρια
    0.06
     ludicrous
    0.06
     চরম
    0.05
    優勝
    0.05
    Activations Density 0.000%

    No Known Activations