© 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. 128675
    Prev
    Next
    INDEX
    Explanations

    announcement of future events

    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
     ابھی
    -0.07
     plenty
    -0.06
     அதில்
    -0.06
     十分
    -0.06
     jednym
    -0.06
     ihtiyaç
    -0.06
     있는데
    -0.06
     estuvo
    -0.06
    Plenty
    -0.06
    是由
    -0.06
    POSITIVE LOGITS
     will
    0.08
    將
    0.07
    将于
    0.06
    将
    0.06
    将在
    0.06
     visto
    0.06
     is
    0.06
     использовать
    0.06
     laure
    0.06
    स्त्री
    0.06
    Activations Density 0.034%

    No Known Activations