© 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. 34-GEMMASCOPE-RES-131K
    7. 55696
    Prev
    Next
    INDEX
    Explanations

    parenthetical citations

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

    The neuron detects four-digit year numbers (publication dates) typically used in scholarly citations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     and
    -1.26
     کامپی
    -0.82
    ganggu
    -0.79
     andere
    -0.78
    😈
    -0.77
    鰐
    -0.76
    겸
    -0.75
     THEIR
    -0.75
    っていて
    -0.74
     dupa
    -0.74
    POSITIVE LOGITS
    ;
    1.00
     wast
    0.91
    スコ
    0.86
    ),
    0.85
     ),
    0.83
    </sup>
    0.79
    irected
    0.79
    
    0.78
     vertraut
    0.78
    вушка
    0.78
    Activations Density 0.005%

    No Known Activations