© 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. 119993
    Prev
    Next
    INDEX
    Explanations

    Chesapeake Bay, Water Improvement District

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ゲ
    -0.06
     suelen
    -0.06
     liberté
    -0.06
     люди
    -0.06
    Urban
    -0.06
     শহরের
    -0.06
    在
    -0.06
     kampus
    -0.06
     городского
    -0.06
     decriminal
    -0.06
    POSITIVE LOGITS
     disappointing
    0.06
     साझा
    0.06
     till
    0.06
     هاش
    0.06
     Macri
    0.06
     shakespeare
    0.06
     বাসিন্দা
    0.06
    缺失
    0.06
     ভাল
    0.06
     chronic
    0.06
    Activations Density 0.006%

    No Known Activations