© 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. 117441
    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
     አበባ
    -0.06
     per
    -0.06
     iluminación
    -0.06
    燈
    -0.06
     ထ
    -0.05
     naïve
    -0.05
    pstmt
    -0.05
    sema
    -0.05
     Treasures
    -0.05
     съем
    -0.05
    POSITIVE LOGITS
     disputes
    0.07
    争议
    0.07
     clashes
    0.07
     disagreements
    0.07
     Drinfeld
    0.07
     clash
    0.06
     camaraderie
    0.06
     pitting
    0.06
     insists
    0.06
     consensual
    0.06
    Activations Density 0.000%

    No Known Activations