© 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. 118229
    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
    理由は
    -0.07
    注册
    -0.07
     but
    -0.07
     nhưng
    -0.07
     nombreuses
    -0.07
    leding
    -0.06
     angiogenesis
    -0.06
     ہمیشہ
    -0.06
     многих
    -0.06
    MANY
    -0.06
    POSITIVE LOGITS
     On
    0.06
     Fabulous
    0.06
     fantastic
    0.06
     different
    0.06
    On
    0.05
     additional
    0.05
     O
    0.05
     on
    0.05
    নগর
    0.05
     proverbial
    0.05
    Activations Density 0.000%

    No Known Activations