© 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. 118356
    Prev
    Next
    INDEX
    Explanations

    cell function or quantities

    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
     breathed
    -0.07
    ision
    -0.06
     merupakan
    -0.06
     contaminating
    -0.06
     だ
    -0.06
     görsel
    -0.06
    ったら
    -0.06
     epile
    -0.06
    logo
    -0.06
     welcomed
    -0.06
    POSITIVE LOGITS
     watchful
    0.06
     convert
    0.06
     щодо
    0.06
    их
    0.05
    分配
    0.05
     وبا
    0.05
     need
    0.05
    Ok
    0.05
     make
    0.05
     দাব
    0.05
    Activations Density 0.010%

    No Known Activations