© 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. 119625
    Prev
    Next
    INDEX
    Explanations

    career

    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
     and
    -0.08
    而
    -0.08
    そして
    -0.06
     ومن
    -0.06
     aktu
    -0.06
     최근
    -0.06
    并通过
    -0.06
    stat
    -0.06
    currently
    -0.06
    Currently
    -0.06
    POSITIVE LOGITS
     подготовки
    0.07
    苦手
    0.07
     नहीं
    0.07
     không
    0.07
     перед
    0.06
     подготовке
    0.06
     watchful
    0.06
     Almanya
    0.06
     так
    0.06
    兩個
    0.06
    Activations Density 0.003%

    No Known Activations