© 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. 22-GEMMASCOPE-RES-131K
    7. 79818
    Prev
    Next
    INDEX
    Explanations

    citation suffixes

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

    This neuron detects in-text citation markers or reference numbers (e.g. “[91]” or “[@228]”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     papillon
    -1.09
     leger
    -1.08
    SEGU
    -1.06
     REGUL
    -1.01
     barna
    -1.00
    ของ
    -0.98
    甥
    -0.98
    掟
    -0.97
     tabac
    -0.97
     roca
    -0.96
    POSITIVE LOGITS
     etc
    1.23
     the
    1.15
     verdaderas
    1.03
     Synag
    1.02
    estrado
    1.00
    etc
    1.00
     embaraz
    1.00
    
    0.99
     skapa
    0.98
    rets
    0.98
    Activations Density 0.035%

    No Known Activations