© 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. 129339
    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
    !
    -0.06
    んだけど
    -0.05
    गुना
    -0.05
    лист
    -0.05
     증가
    -0.05
     দেবে
    -0.05
     menjel
    -0.05
     incub
    -0.05
     Du
    -0.05
     encuent
    -0.05
    POSITIVE LOGITS
    Christopher
    0.06
     refused
    0.06
     como
    0.06
     horas
    0.06
     as
    0.06
     केन्द्रीय
    0.06
     writing
    0.06
     отказа
    0.06
     hydrolysis
    0.06
     Christopher
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.