© 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. 117979
    Prev
    Next
    INDEX
    Explanations

    8

    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
    ppu
    -0.07
     four
    -0.06
     يوجد
    -0.06
     dispon
    -0.06
    없
    -0.05
     najważ
    -0.05
     two
    -0.05
     numerous
    -0.05
     σημαν
    -0.05
    螺旋
    -0.05
    POSITIVE LOGITS
     做
    0.07
    类似于
    0.07
     being
    0.06
    扔
    0.06
     będzie
    0.06
     atualmente
    0.06
     will
    0.06
    Antae
    0.06
     以
    0.06
    くなる
    0.06
    Activations Density 0.007%

    No Known Activations