© 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. 129109
    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
     but
    -0.07
     কিন্তু
    -0.07
     लेकिन
    -0.06
    แต่
    -0.06
     nhưng
    -0.06
    ॉयड
    -0.06
     근데
    -0.06
     kinds
    -0.06
     więcej
    -0.06
     αλλά
    -0.06
    POSITIVE LOGITS
     einzigen
    0.07
     gemakkelijk
    0.06
    完全に
    0.06
     solamente
    0.06
    വേശ
    0.06
     Очень
    0.06
    ONLY
    0.06
     hanya
    0.06
    Ras
    0.06
     conforme
    0.06
    Activations Density 0.000%

    No Known Activations