© 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. 119564
    Prev
    Next
    INDEX
    Explanations

    Former leaders

    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
    òu
    -0.07
     جديدة
    -0.07
    }}}}$
    -0.06
     الجديدة
    -0.06
     হে
    -0.06
     सांस्कृतिक
    -0.06
    ですよ
    -0.06
    是一些
    -0.06
     테스트
    -0.06
     nuova
    -0.06
    POSITIVE LOGITS
     सर्वप्रथम
    0.06
     tireless
    0.06
     leader
    0.06
     책임
    0.06
    直至
    0.06
     नेते
    0.06
     leaders
    0.06
     unab
    0.06
    直到
    0.06
     leading
    0.06
    Activations Density 0.003%

    No Known Activations