© 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. 130041
    Prev
    Next
    INDEX
    Explanations

    units of measure

    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
     almac
    -0.07
     depends
    -0.06
     зависимости
    -0.06
     соответствует
    -0.06
     نتع
    -0.06
    と
    -0.06
     അവിടെ
    -0.06
     Москва
    -0.06
     يب
    -0.06
     какой
    -0.06
    POSITIVE LOGITS
     ढक
    0.06
     midweek
    0.06
     gifted
    0.06
     مثل
    0.05
     employed
    0.05
     imperfect
    0.05
     entirety
    0.05
    蘚
    0.05
     jedoch
    0.05
    ريس
    0.05
    Activations Density 0.049%

    No Known Activations