© 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. 129574
    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
    cius
    -0.07
     엄청
    -0.06
    Jensen
    -0.06
     тебя
    -0.06
    說明
    -0.06
     Importance
    -0.06
    importance
    -0.05
     если
    -0.05
     الرسمي
    -0.05
    ിക്കാം
    -0.05
    POSITIVE LOGITS
     later
    0.07
     of
    0.07
     เพื่อน
    0.06
     raconte
    0.06
     in
    0.06
     one
    0.06
    以後
    0.06
     אחר
    0.06
     később
    0.06
     же
    0.06
    Activations Density 0.000%

    No Known Activations