© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129960
    Prev
    Next
    INDEX
    Explanations

    names like Robin, Anne, Tony, Paul

    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
     বিপর্যয়
    -0.06
    ენტ
    -0.06
     Fourier
    -0.06
     назнача
    -0.06
    ໋
    -0.06
     fashionable
    -0.06
     gradually
    -0.06
    ówno
    -0.06
     სისტ
    -0.06
     teda
    -0.06
    POSITIVE LOGITS
    ↵
    0.08
     А
    0.07
     Kati
    0.06
    ‌‌
    0.06
     Ð
    0.06
     If
    0.06
     большим
    0.06
     आपका
    0.06
    ↩
    0.06
     большого
    0.06
    Activations Density 0.004%

    No Known Activations