© 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. 20519
    Prev
    Next
    INDEX
    Explanations

    trustee or executor official

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

    The neuron fires on occurrences of “Trust” and “Trustee” (and related institutional trust terms) in legal case headings.

    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
     about
    -1.48
    recently
    -1.43
    erm
    -1.38
    ”？
    -1.37
     recientes
    -1.37
     recientemente
    -1.35
    どれも
    -1.31
     armario
    -1.29
    ﮕ
    -1.28
    相変わらず
    -1.27
    POSITIVE LOGITS
    cherichia
    1.49
    Ի
    1.40
     удалить
    1.39
    能
    1.37
     want
    1.35
    ۸
    1.34
     wants
    1.34
     eeuw
    1.33
    ggiata
    1.32
    ској
    1.31
    Activations Density 0.067%

    No Known Activations