© 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. 128937
    Prev
    Next
    INDEX
    Explanations

    published by

    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
    :
    -0.11
    ,
    -0.09
    -
    -0.07
    ，
    -0.07
     -
    -0.07
     :
    -0.06
    re
    -0.06
     после
    -0.06
     özellikle
    -0.05
     co
    -0.05
    POSITIVE LOGITS
     Produ
    0.07
     kiddos
    0.06
     måste
    0.06
     några
    0.06
     beberapa
    0.06
     মন্ত্রণালয়ের
    0.06
    Produ
    0.06
     pocos
    0.06
     ország
    0.06
     citrus
    0.06
    Activations Density 0.003%

    No Known Activations