© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117750
    Prev
    Next
    INDEX
    Explanations

    foreign words for including

    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
    ?
    -0.06
     பற்றிய
    -0.06
    ﻕ
    -0.06
    &
    -0.06
    ੀ
    -0.05
    вле
    -0.05
    8
    -0.05
    full
    -0.05
     reda
    -0.05
     দেখিয়ে
    -0.05
    POSITIVE LOGITS
     включая
    0.07
     포함
    0.07
     uključ
    0.07
     ઉપરાંત
    0.07
     inklusive
    0.06
    thema
    0.06
     includ
    0.06
     selecciona
    0.06
    konen
    0.06
    gameObjects
    0.06
    Activations Density 0.003%

    No Known Activations