© 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. 130152
    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
    合法
    -0.06
    Activity
    -0.06
    osh
    -0.05
     disinfect
    -0.05
     exemplify
    -0.05
     Activity
    -0.05
    Jacob
    -0.05
     loại
    -0.05
    示范
    -0.05
    य्
    -0.05
    POSITIVE LOGITS
     νέ
    0.07
     ранее
    0.07
    更容易
    0.07
     former
    0.07
     Subsequently
    0.07
     daha
    0.06
    říve
    0.06
     subsequently
    0.06
     omoguć
    0.06
     wcześniej
    0.06
    Activations Density 0.000%

    No Known Activations