© 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. 119866
    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
    တွင်
    -0.07
    於
    -0.06
    정에
    -0.06
     shall
    -0.06
    και
    -0.06
    Shall
    -0.06
    服装
    -0.06
     Not
    -0.06
     אין
    -0.06
    ใน
    -0.06
    POSITIVE LOGITS
     achievement
    0.06
    黏
    0.06
    を表
    0.06
    ｰ
    0.06
    isati
    0.06
    ।
    0.06
     KPI
    0.06
     manufacturer
    0.06
    achievement
    0.06
     Achievement
    0.06
    Activations Density 0.000%

    No Known Activations