© 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. 118702
    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
    他们
    -0.07
    他们的
    -0.07
    だけで
    -0.07
    他們
    -0.06
     उन्हें
    -0.06
    onto
    -0.06
    针对
    -0.06
     onları
    -0.06
    㷫
    -0.06
     उनको
    -0.06
    POSITIVE LOGITS
     which
    0.07
     antes
    0.07
     που
    0.06
    ដែល
    0.06
     हा
    0.06
     التي
    0.06
     như
    0.06
     πριν
    0.06
     when
    0.06
     that
    0.06
    Activations Density 0.000%

    No Known Activations