© 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. 118049
    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
     banyak
    -0.06
     ይህ
    -0.06
     st
    -0.05
     creates
    -0.05
     カ
    -0.05
     ويع
    -0.05
     使用
    -0.05
    娶
    -0.05
    简单的
    -0.05
    Every
    -0.05
    POSITIVE LOGITS
     DHCP
    0.07
    这意味着
    0.07
    :
    0.07
     ----->
    0.06
    ということです
    0.06
     ऑलरेडी
    0.06
     the
    0.06
     справа
    0.06
    开发者
    0.06
    ެއް
    0.06
    Activations Density 0.000%

    No Known Activations