© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130415
    Prev
    Next
    INDEX
    Explanations

    **second member**

    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
    있
    -0.07
     no
    -0.06
     initially
    -0.06
     všet
    -0.06
     lahat
    -0.06
     جميع
    -0.06
     all
    -0.06
     have
    -0.06
     wówczas
    -0.06
     kõik
    -0.06
    POSITIVE LOGITS
     spoonful
    0.06
     Stakes
    0.06
    堈
    0.06
     পরস্প
    0.06
     فهم
    0.06
     applies
    0.06
     finalizing
    0.06
    ﺛ
    0.06
    espère
    0.06
    是一些
    0.05
    Activations Density 0.102%

    No Known Activations