© 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. 68799
    Prev
    Next
    INDEX
    Explanations

    proceedings of

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

    This neuron detects bibliographic citation phrases, especially instances of “Proceedings of” in reference entries.

    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
     każdy
    -1.70
    얏
    -1.65
    動き
    -1.63
    geſ
    -1.60
     Voraussetzung
    -1.59
     同
    -1.58
    鬟
    -1.56
    ⸥
    -1.54
    pherds
    -1.54
     menggunakan
    -1.54
    POSITIVE LOGITS
    ,
    1.74
    瑧
    1.57
     mães
    1.57
     Not
    1.55
     pulau
    1.54
    鈰
    1.54
     haki
    1.50
    烔
    1.46
    茘
    1.45
    '
    1.42
    Activations Density 0.002%

    No Known Activations