© 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. 129330
    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
     প্রধানমন্ত্রী
    -0.07
     migliorare
    -0.07
    当天
    -0.07
    כת
    -0.06
     제공
    -0.06
     Imagine
    -0.06
    一般来说
    -0.06
     harrowing
    -0.06
     Partial
    -0.06
    imagine
    -0.06
    POSITIVE LOGITS
    ,
    0.08
    oubtedly
    0.05
     leur
    0.05
    mores
    0.05
    ar
    0.05
    名字
    0.05
    的名字
    0.05
    몹
    0.05
     अधिव
    0.05
     eye
    0.05
    Activations Density 0.000%

    No Known Activations