© 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. 119474
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions or code comments

    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
     previos
    -0.07
     which
    -0.07
     GENERAL
    -0.06
     первую
    -0.06
     tačiau
    -0.06
    احمد
    -0.06
     आदान
    -0.06
     प्राथमिक
    -0.06
     penggunaan
    -0.06
    ರ್ಚ
    -0.06
    POSITIVE LOGITS
     વેબસ
    0.06
     ans
    0.06
     अश
    0.05
    Fully
    0.05
    Err
    0.05
    timed
    0.05
    Unlike
    0.05
    䉿
    0.05
     Dá
    0.05
     ////
    0.05
    Activations Density 0.001%

    No Known Activations