© 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. 119731
    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
     снова
    -0.07
     there
    -0.07
     ignorance
    -0.06
    用
    -0.06
     서로
    -0.06
     অনুসন্ধ
    -0.06
    ignor
    -0.06
    there
    -0.06
     There
    -0.06
     Either
    -0.06
    POSITIVE LOGITS
     vaan
    0.06
     đáng
    0.06
     കുടുംബ
    0.06
     blessing
    0.06
     частини
    0.05
     வாழ
    0.05
     其他
    0.05
    δευ
    0.05
    );
    0.05
     подпис
    0.05
    Activations Density 0.000%

    No Known Activations