© 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. 119434
    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
     also
    -0.08
    也很
    -0.07
    也非常
    -0.07
     또한
    -0.07
     также
    -0.07
     anthropology
    -0.06
    也是
    -0.06
     the
    -0.06
    hese
    -0.06
    就这样
    -0.06
    POSITIVE LOGITS
     asignar
    0.06
    我們會
    0.06
    емые
    0.06
     kool
    0.06
     null
    0.06
    ที่เรา
    0.06
     norme
    0.06
     nulle
    0.06
     NULL
    0.06
     renegoti
    0.06
    Activations Density 0.000%

    No Known Activations