© 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. 117240
    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
     ketika
    -0.07
     nhưng
    -0.07
    是因为
    -0.07
     예술
    -0.07
     لكن
    -0.07
    Thankfully
    -0.06
    bundled
    -0.06
     unable
    -0.06
    했지만
    -0.06
     있지만
    -0.06
    POSITIVE LOGITS
    兩
    0.06
    名词
    0.06
    两
    0.05
     下
    0.05
    wj
    0.05
    াক্তন
    0.05
     tiga
    0.05
     গভীর
    0.05
    beda
    0.05
     name
    0.05
    Activations Density 0.000%

    No Known Activations