© 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. 13877
    Prev
    Next
    INDEX
    Explanations

    citation numbers and punctuation

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

    This neuron responds to numeric citation details (years, volume/issue numbers, page ranges) in academic references.

    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
     ostensibly
    -2.03
    For
    -2.02
     it
    -1.95
     meticulously
    -1.93
     what
    -1.89
     swiftly
    -1.85
     blatantly
    -1.85
    What
    -1.84
    K
    -1.83
    It
    -1.79
    POSITIVE LOGITS
     Dinas
    2.05
    ’-
    1.93
     quí
    1.91
    甗
    1.83
     REQUIRE
    1.82
     wacky
    1.81
     DIFFERENT
    1.80
    opies
    1.79
     soooo
    1.78
     LOST
    1.78
    Activations Density 0.001%

    No Known Activations