© 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. 118119
    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
    。
    -0.07
     marital
    -0.07
    (),
    -0.06
     has
    -0.06
     тази
    -0.06
    ))),
    -0.06
     и
    -0.06
     не
    -0.06
    😊
    -0.06
     toilet
    -0.06
    POSITIVE LOGITS
     following
    0.07
     you
    0.06
    ధం
    0.06
    </img>
    0.06
    following
    0.06
     তুই
    0.06
     我
    0.06
     generali
    0.06
     mengikuti
    0.05
     অনিবার
    0.05
    Activations Density 0.000%

    No Known Activations