© 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. 128479
    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
     сначала
    -0.06
     Educational
    -0.06
     rov
    -0.06
    luğ
    -0.06
    educational
    -0.06
    Educational
    -0.06
     التر
    -0.06
     eerst
    -0.06
    泹
    -0.05
    how
    -0.05
    POSITIVE LOGITS
     ইতিমধ্যেই
    0.07
    既に
    0.06
     ইতিমধ্যে
    0.06
     occuring
    0.06
     tidigare
    0.06
     недавно
    0.06
    我已经
    0.06
     smile
    0.06
    及び
    0.06
     فونٹ
    0.06
    Activations Density 0.000%

    No Known Activations