© 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. 120411
    Prev
    Next
    INDEX
    Explanations

    eclipse

    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
     पहुँच
    -0.06
     ಅವರು
    -0.06
     فارسی
    -0.06
     bunları
    -0.06
    獐
    -0.06
     일이
    -0.06
    ಗಳಲ್ಲಿ
    -0.05
     darg
    -0.05
     existing
    -0.05
     असले
    -0.05
    POSITIVE LOGITS
     हमने
    0.06
     quién
    0.06
     små
    0.06
    Anon
    0.06
     Tiny
    0.06
    ))),
    0.06
     ভিডি
    0.06
     Anon
    0.06
     кін
    0.06
    médiaire
    0.06
    Activations Density 0.004%

    No Known Activations