© 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. 117370
    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
    任意の
    -0.07
     suitors
    -0.07
    別人
    -0.07
    别人
    -0.06
    ඃ
    -0.06
    ターゲット
    -0.06
     neue
    -0.06
     আদালতের
    -0.06
    Popular
    -0.06
     recognize
    -0.06
    POSITIVE LOGITS
     cann
    0.06
    fl
    0.06
     hInstance
    0.06
    плом
    0.06
    פר
    0.06
    sized
    0.06
    bete
    0.06
    erie
    0.06
     দ্র
    0.06
     swallowed
    0.05
    Activations Density 0.000%

    No Known Activations