© 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. 118942
    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
    atives
    -0.06
     सीएचसी
    -0.06
     छात्रावास
    -0.06
     প্রাচ
    -0.06
    árez
    -0.06
    جموع
    -0.06
     procedures
    -0.06
    㳳
    -0.06
    𝜁
    -0.06
     deset
    -0.06
    POSITIVE LOGITS
     தெளி
    0.06
     जिसमें
    0.06
     clearer
    0.06
     shampoo
    0.06
     handled
    0.05
     optional
    0.05
     lifeboat
    0.05
     부분이
    0.05
     anglers
    0.05
     algae
    0.05
    Activations Density 0.000%

    No Known Activations