© 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. 129571
    Prev
    Next
    INDEX
    Explanations

    release dates

    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
     Announcement
    -0.07
     expected
    -0.07
     announcement
    -0.07
    Announcement
    -0.07
    expected
    -0.07
    设计
    -0.07
    この
    -0.06
    可能会
    -0.06
    的消息
    -0.06
     не
    -0.06
    POSITIVE LOGITS
    ots
    0.06
    ܨ
    0.06
     maupun
    0.06
    DEFIN
    0.06
     عندها
    0.06
    aliment
    0.06
     omnichannel
    0.06
     deepening
    0.06
     buffs
    0.06
     you
    0.06
    Activations Density 0.018%

    No Known Activations