© 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. 117565
    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
    瞬间
    -0.07
     двох
    -0.07
     costs
    -0.07
     दोन
    -0.06
     vedno
    -0.06
     голе
    -0.06
     realistic
    -0.06
    কারি
    -0.06
     поэтому
    -0.06
     sized
    -0.06
    POSITIVE LOGITS
    基本的
    0.07
     बेसिक
    0.07
     básicas
    0.06
     வலியுறு
    0.06
     পশ্চিমে
    0.06
     basic
    0.06
    ธิ
    0.06
     concerning
    0.06
     barba
    0.06
    的基本
    0.06
    Activations Density 0.000%

    No Known Activations