© 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. 119170
    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
    Should
    -0.07
    Are
    -0.07
    Would
    -0.06
     عن
    -0.06
     pozit
    -0.06
     shu
    -0.06
     larger
    -0.06
    iger
    -0.06
     희
    -0.06
     contemplated
    -0.06
    POSITIVE LOGITS
     first
    0.07
     使用
    0.06
     almeno
    0.06
    结束
    0.06
    oea
    0.06
    친구
    0.06
     continues
    0.06
    Latin
    0.06
     fostered
    0.06
     terminó
    0.06
    Activations Density 0.000%

    No Known Activations