© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130736
    Prev
    Next
    INDEX
    Explanations

    category of

    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
     삶
    -0.07
     життя
    -0.06
     बस्ती
    -0.05
     wygląd
    -0.05
     gyven
    -0.05
    iren
    -0.05
    ያንዳ
    -0.05
    あらゆる
    -0.05
    uited
    -0.05
    mash
    -0.05
    POSITIVE LOGITS
     ponad
    0.07
     if
    0.07
     Considerable
    0.06
     रोजाना
    0.06
     میتوان
    0.06
     około
    0.06
    御
    0.06
     Dentro
    0.06
     系
    0.06
    eynman
    0.06
    Activations Density 0.007%

    No Known Activations