© 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. 128940
    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
     መካከል
    -0.06
    ダイエット
    -0.06
    同様
    -0.06
     касается
    -0.06
    ിട
    -0.06
     पीछ
    -0.06
    彡
    -0.06
    tera
    -0.06
     actúa
    -0.06
    urgia
    -0.06
    POSITIVE LOGITS
     necessary
    0.06
     डिस्प्ले
    0.06
     ainsi
    0.06
    ACE
    0.06
     oraz
    0.06
    objPHPExcel
    0.06
     associated
    0.05
    เริ่ม
    0.05
    সম্প
    0.05
    AsString
    0.05
    Activations Density 0.000%

    No Known Activations