© 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. 117855
    Prev
    Next
    INDEX
    Explanations

    court clerk names

    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
    apply
    -0.06
     pleasures
    -0.06
    enske
    -0.06
    自宅
    -0.06
    Moving
    -0.06
    Songs
    -0.05
     Something
    -0.05
    ⼊
    -0.05
     pf
    -0.05
     tugas
    -0.05
    POSITIVE LOGITS
     میلیارد
    0.07
     zejména
    0.06
     भी
    0.06
     επίσης
    0.06
     полноцен
    0.06
     passare
    0.06
    来了
    0.05
     RIGHT
    0.05
     অস্ব
    0.05
     alleged
    0.05
    Activations Density 0.004%

    No Known Activations