© 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. 116593
    Prev
    Next
    INDEX
    Explanations

    mathematical sequences

    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
    odie
    -0.06
     बुरी
    -0.06
     nearby
    -0.06
     considerations
    -0.06
    드를
    -0.06
     ইংল্যান্ড
    -0.06
     colegas
    -0.06
     insan
    -0.06
     सेंट
    -0.06
     voed
    -0.06
    POSITIVE LOGITS
     المرأة
    0.05
     tersebut
    0.05
    Pagination
    0.05
     aquela
    0.05
     MTN
    0.05
    详情
    0.05
     Ships
    0.05
     després
    0.05
    poch
    0.05
     tieto
    0.05
    Activations Density 0.002%

    No Known Activations