© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20230
    Prev
    Next
    INDEX
    Explanations

    Deputy followed by title

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

    The neuron detects instances of the formal title “Deputy” in legal‐document 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
    ."
    -3.03
    餮
    -2.81
    iyaki
    -2.72
    icksburg
    -2.70
     '
    -2.61
    內容簡介
    -2.59
    趿
    -2.58
     immense
    -2.55
     wichtigste
    -2.53
    '
    -2.53
    POSITIVE LOGITS
    replyreport
    3.05
    妺
    2.44
     However
    2.42
     lograr
    2.41
    スポンサーリンク
    2.41
    オ
    2.34
     незавер
    2.34
     chcesz
    2.33
    0
    2.33
     sedia
    2.31
    Activations Density 0.005%

    No Known Activations