© 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. 129116
    Prev
    Next
    INDEX
    Explanations

    Retro Announcement

    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
    usable
    -0.06
     associ
    -0.06
    leyin
    -0.06
     utilis
    -0.05
     utiliser
    -0.05
    ற்போது
    -0.05
     নামটি
    -0.05
     uży
    -0.05
     compared
    -0.05
    POSITIVE LOGITS
     වෙන
    0.07
    वाई
    0.07
     tengo
    0.07
     각
    0.06
    tenant
    0.06
    শরণ
    0.06
     различни
    0.06
     важли
    0.06
     hvert
    0.06
     каждая
    0.06
    Activations Density 0.003%

    No Known Activations