© 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. 116951
    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
    should
    -0.08
     should
    -0.07
     our
    -0.07
    我们的
    -0.07
    应该
    -0.07
    我們的
    -0.06
     jsou
    -0.06
     ہماری
    -0.06
    栆
    -0.06
     unserem
    -0.06
    POSITIVE LOGITS
     für
    0.06
     use
    0.06
    စာ
    0.06
     for
    0.06
    ्यर्थ
    0.06
     fácil
    0.06
    वारीत
    0.05
    ↵↵↵↵↵↵↵↵↵↵↵
    0.05
     для
    0.05
    ácil
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.