© 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. 120026
    Prev
    Next
    INDEX
    Explanations

    at

    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
     finalmente
    -0.07
     finally
    -0.07
     official
    -0.07
     Finalmente
    -0.06
    ℹ
    -0.06
     potwier
    -0.06
     coming
    -0.06
     arrivée
    -0.06
     final
    -0.06
     FINAL
    -0.06
    POSITIVE LOGITS
    Presentation
    0.08
     presentation
    0.07
     Presentation
    0.07
     apresentação
    0.07
     exploration
    0.07
     présenter
    0.07
     presenter
    0.07
     create
    0.07
     मातरम
    0.06
    Presenter
    0.06
    Activations Density 0.026%

    No Known Activations