© 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. 129341
    Prev
    Next
    INDEX
    Explanations

    for example

    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
     and
    -0.09
    そして
    -0.07
    /
    -0.07
    ＆
    -0.07
     ও
    -0.06
     anis
    -0.06
     다양한
    -0.06
     &
    -0.06
    而
    -0.06
     மற்றும்
    -0.06
    POSITIVE LOGITS
     esimerkiksi
    0.09
    比如
    0.09
     যেমন
    0.08
     misalnya
    0.08
     مثلا
    0.08
     például
    0.07
     например
    0.07
     bijvoorbeeld
    0.07
    比如说
    0.07
    例えば
    0.07
    Activations Density 0.038%

    No Known Activations