© 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. 120456
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    :
    -0.07
     بعدی
    -0.06
     cuối
    -0.06
    ¹
    -0.06
     aha
    -0.06
     теперь
    -0.06
     daqui
    -0.06
     이후
    -0.05
     igény
    -0.05
    шкой
    -0.05
    POSITIVE LOGITS
     dhammo
    0.08
    任何
    0.06
     ப்ளாக்
    0.06
     ஸ்ட
    0.06
     antimony
    0.06
    レイ
    0.06
    Impossible
    0.06
     philosophies
    0.06
     cualquier
    0.06
    簡單
    0.06
    Activations Density 0.000%

    No Known Activations