© 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. 120359
    Prev
    Next
    INDEX
    Explanations

    file header

    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
     decreasing
    -0.05
     Alert
    -0.05
     $-\
    -0.05
     coraz
    -0.05
    ◈
    -0.05
    anyone
    -0.05
     Latinoamérica
    -0.05
    ={<
    -0.05
     (<
    -0.05
     заседа
    -0.05
    POSITIVE LOGITS
     программу
    0.06
     gols
    0.06
    Would
    0.06
     프로그램을
    0.06
    匀
    0.06
     خیلی
    0.06
     economico
    0.06
    如今
    0.06
    实际
    0.06
    มัน
    0.06
    Activations Density 0.001%

    No Known Activations