© 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. 117176
    Prev
    Next
    INDEX
    Explanations

    code assignment operator

    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
     ensinar
    -0.06
    昔
    -0.06
     такі
    -0.06
     Altogether
    -0.06
     gratifying
    -0.06
    详情
    -0.06
     محدود
    -0.06
     самим
    -0.06
     dáv
    -0.06
     صع
    -0.06
    POSITIVE LOGITS
     și
    0.06
    control
    0.06
     বিষয়ের
    0.06
     it
    0.06
     onto
    0.06
     ঘণ্টার
    0.05
    ournal
    0.05
     doesn
    0.05
     opciones
    0.05
     knee
    0.05
    Activations Density 0.003%

    No Known Activations