© 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. 129682
    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
     cũng
    -0.06
     more
    -0.06
    も
    -0.06
    もし
    -0.06
    还会
    -0.06
     predic
    -0.06
     also
    -0.06
     nebo
    -0.05
    会
    -0.05
     continual
    -0.05
    POSITIVE LOGITS
     with
    0.06
     alors
    0.06
     which
    0.06
     mahdoll
    0.06
     hitherto
    0.06
     ketiga
    0.06
    ÍT
    0.06
     außergewöhn
    0.06
    หนึ่ง
    0.06
     אחד
    0.06
    Activations Density 0.000%

    No Known Activations