© 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. 119520
    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
     distinctive
    -0.06
     one
    -0.06
     رد
    -0.06
    šek
    -0.06
     फी
    -0.06
     fascinating
    -0.06
    िटल
    -0.06
     fiz
    -0.06
     conditional
    -0.05
    Distinct
    -0.05
    POSITIVE LOGITS
     septembre
    0.07
    無い
    0.06
     passende
    0.06
     gerekli
    0.06
     necessario
    0.06
     rentrer
    0.06
    unlike
    0.06
    ওয়ে
    0.06
    無し
    0.06
     দেবেন
    0.06
    Activations Density 0.000%

    No Known Activations