© 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. 118134
    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
     हमारी
    -0.06
    cluding
    -0.06
     confort
    -0.06
     genesis
    -0.06
     serviços
    -0.06
     म्हणजेच
    -0.06
    Jeśli
    -0.06
    hankelijk
    -0.05
     Protecting
    -0.05
    Proj
    -0.05
    POSITIVE LOGITS
     umfang
    0.07
     pudieran
    0.06
     কয়
    0.06
    法轮
    0.06
    起こ
    0.06
     چندین
    0.06
     routinely
    0.06
     existente
    0.06
     ચૂંટણી
    0.06
    Bed
    0.06
    Activations Density 0.000%

    No Known Activations