© 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. 128925
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    んでいます
    -0.06
     celui
    -0.06
     لماذا
    -0.06
    Bound
    -0.06
     kyun
    -0.06
     नव्या
    -0.06
     why
    -0.06
     യുവാ
    -0.06
     Celui
    -0.06
     တ
    -0.06
    POSITIVE LOGITS
    ,
    0.09
    根據
    0.07
    根据
    0.07
     mussten
    0.07
     根据
    0.06
    ™,
    0.06
     שה
    0.06
     diketahui
    0.06
     হতে
    0.06
    🛴
    0.06
    Activations Density 0.002%

    No Known Activations