© 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. 130284
    Prev
    Next
    INDEX
    Explanations

    reducing sugar

    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
     ширина
    -0.06
     Lorenz
    -0.06
    ‌ന
    -0.05
    ip
    -0.05
     daarbij
    -0.05
    uz
    -0.05
    β
    -0.05
    쭉
    -0.05
    féle
    -0.05
    ohr
    -0.05
    POSITIVE LOGITS
     同じ
    0.07
     Đế
    0.07
    后的
    0.07
    同じ
    0.06
    を迎
    0.06
    ंबर्स
    0.06
     आफ्टर
    0.06
    Gonzalez
    0.06
     അധികാര
    0.06
     AFTER
    0.06
    Activations Density 0.003%

    No Known Activations