© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130660
    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
    awać
    -0.07
     incluir
    -0.06
     interesses
    -0.06
     henüz
    -0.06
    ડે
    -0.06
     motive
    -0.06
     방법을
    -0.06
     plataforma
    -0.06
     нема
    -0.06
     pioneered
    -0.06
    POSITIVE LOGITS
     من
    0.06
     дальше
    0.06
     Now
    0.06
     પરંતુ
    0.06
    Now
    0.05
    Ny
    0.05
    有
    0.05
     Talk
    0.05
    その
    0.05
    んだけど
    0.05
    Activations Density 0.000%

    No Known Activations