© 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. 129282
    Prev
    Next
    INDEX
    Explanations

    #include directives

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Using
    -0.07
     utilisez
    -0.07
     использованием
    -0.07
     untuk
    -0.07
     Untuk
    -0.07
     gebruik
    -0.07
    Using
    -0.07
     использования
    -0.07
     utilizzare
    -0.07
     использование
    -0.07
    POSITIVE LOGITS
     فائد
    0.06
    widehat
    0.06
     would
    0.06
     fiancée
    0.05
     here
    0.05
     সত্ত
    0.05
     everybody
    0.05
     aquí
    0.05
    -
    0.05
     dirinya
    0.05
    Activations Density 0.006%

    No Known Activations