© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129570
    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
    昃
    -0.07
    是一個
    -0.06
    是一个
    -0.06
     October
    -0.06
     dünyaya
    -0.06
    を使う
    -0.06
    过程中
    -0.06
     Don
    -0.06
     कन्या
    -0.06
    きっと
    -0.06
    POSITIVE LOGITS
    ;
    0.07
     مثل
    0.07
     such
    0.07
     the
    0.06
     nitride
    0.06
     idioms
    0.06
     Leipzig
    0.05
     impug
    0.05
     prophecies
    0.05
     traverses
    0.05
    Activations Density 0.000%

    No Known Activations