© 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. 129638
    Prev
    Next
    INDEX
    Explanations

    month, day, or year

    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
    ast
    -0.06
    مره
    -0.06
    <0xE3>
    -0.06
    adham
    -0.06
    েক
    -0.06
     চিত্রক
    -0.05
    By
    -0.05
    Up
    -0.05
    こちらは
    -0.05
    ようです
    -0.05
    POSITIVE LOGITS
     다섯
    0.08
    会导致
    0.07
     erkek
    0.07
     пяти
    0.07
     Ambiente
    0.07
     histidine
    0.07
     jing
    0.07
     cinco
    0.06
     njihov
    0.06
    特点
    0.06
    Activations Density 0.003%

    No Known Activations