© 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. 119058
    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
    今年
    -0.06
    ära
    -0.06
    對
    -0.06
     ধীরে
    -0.06
    新年
    -0.06
    对
    -0.06
     他
    -0.06
    सत
    -0.06
     již
    -0.06
     的
    -0.06
    POSITIVE LOGITS
    reachable
    0.06
     cuando
    0.06
     forty
    0.06
    ቶችን
    0.06
     finalement
    0.06
     তেমনি
    0.06
     complicates
    0.06
    ज़्
    0.06
    paround
    0.06
    నా
    0.06
    Activations Density 0.000%

    No Known Activations