© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104251
    Prev
    Next
    INDEX
    Explanations

    New York City courts

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects references to specific federal appellate courts, especially mentions of the “Second Circuit.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵↵
    -1.41
    :“
    -1.41
    ۶
    -1.40
    、
    -1.37
    ”.
    -1.31
    3
    -1.26
    ۷
    -1.23
    ：
    -1.23
     präsenti
    -1.22
    ,“
    -1.20
    POSITIVE LOGITS
     conseillé
    1.37
    rafas
    1.35
    ziali
    1.34
    PORARY
    1.34
    OURCES
    1.33
    Mujer
    1.32
    djangoproject
    1.31
    涧
    1.31
    queiro
    1.31
     NYPD
    1.30
    Activations Density 0.765%

    No Known Activations