© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128626
    Prev
    Next
    INDEX
    Explanations

    text formatting and code snippets

    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
    aughty
    -0.06
    と
    -0.06
     अपघात
    -0.06
    という
    -0.06
    ორი
    -0.06
     biodivers
    -0.06
    ซึ่ง
    -0.06
     daripada
    -0.06
    delicious
    -0.06
     yaptığı
    -0.06
    POSITIVE LOGITS
     "***
    0.06
     my
    0.06
     "";
    0.06
     removal
    0.06
     zmiany
    0.06
    Agree
    0.06
    এর
    0.05
     பயன்ப
    0.05
     meinem
    0.05
     cambios
    0.05
    Activations Density 0.001%

    No Known Activations