© 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. 117139
    Prev
    Next
    INDEX
    Explanations

    known as, Luck now, Black pine, Worker ‘

    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
     শুদ্ধ
    -0.06
     hundred
    -0.06
     nominally
    -0.06
     заказа
    -0.06
     these
    -0.06
    দম
    -0.06
     passengers
    -0.06
    كه
    -0.06
    injection
    -0.06
     पेशकश
    -0.06
    POSITIVE LOGITS
     obses
    0.08
     вернуть
    0.07
     필수
    0.06
     chimie
    0.06
     química
    0.06
     celui
    0.06
     chemicals
    0.06
     zbyt
    0.06
     Tasmania
    0.06
     chemistry
    0.06
    Activations Density 0.003%

    No Known Activations