© 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. 118832
    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
     тобто
    -0.06
     cioè
    -0.06
     내부
    -0.06
    他是
    -0.06
    注意事项
    -0.06
     yani
    -0.06
     ovvero
    -0.06
    しかない
    -0.06
     дат
    -0.06
    他の
    -0.06
    POSITIVE LOGITS
    ;
    0.07
     daha
    0.06
     Peng
    0.06
    相當
    0.06
     better
    0.06
     be
    0.06
    相当
    0.06
     stronger
    0.06
    轻松
    0.06
     कमजोर
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.