© 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. 119781
    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
     are
    -0.09
    เพราะ
    -0.07
     because
    -0.07
    μαστε
    -0.06
    <tr>
    -0.06
     vì
    -0.06
     gode
    -0.06
     különböző
    -0.06
     innych
    -0.06
    த்திற்காக
    -0.06
    POSITIVE LOGITS
     если
    0.08
     скорее
    0.08
     могло
    0.08
     اگر
    0.07
     могла
    0.07
    Если
    0.07
    Probably
    0.07
    如果
    0.07
     seemed
    0.07
     probably
    0.07
    Activations Density 0.000%

    No Known Activations