© 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. 119446
    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
     Such
    -0.07
     chef
    -0.06
    Such
    -0.06
     along
    -0.06
    まさに
    -0.06
    结果
    -0.06
     alleviate
    -0.06
     الاحت
    -0.05
     Hate
    -0.05
     हनी
    -0.05
    POSITIVE LOGITS
    .
    0.07
    ;
    0.07
     compagn
    0.06
    。
    0.06
     পাবার
    0.06
    );
    0.06
     линии
    0.06
     ス
    0.06
    添加到
    0.06
    将被
    0.06
    Activations Density 0.000%

    No Known Activations