© 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. 116295
    Prev
    Next
    INDEX
    Explanations

    career History

    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
     ALL
    -0.07
    すべて
    -0.07
    全部
    -0.07
     skeptical
    -0.06
     全
    -0.06
     all
    -0.06
     MAR
    -0.06
    बिट
    -0.06
     densely
    -0.06
     Despite
    -0.06
    POSITIVE LOGITS
     людей
    0.07
     people
    0.07
    いくつか
    0.06
     नहा
    0.06
     Bedarf
    0.06
    Adding
    0.06
    رجال
    0.06
     কেউই
    0.06
     or
    0.06
     몇
    0.06
    Activations Density 0.003%

    No Known Activations