© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32731
    Prev
    Next
    INDEX
    Explanations

    citing unpublished

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

    The neuron fires on terms referring to citations or references (e.g. “citation,” “cited,” “reference”).

    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
    ъм
    -0.82
    xspace
    -0.82
    פורט
    -0.81
    вига
    -0.79
    桐
    -0.78
    桧
    -0.77
    Törté
    -0.77
    hdf
    -0.76
     considération
    -0.76
    /-/
    -0.76
    POSITIVE LOGITS
     sources
    2.97
     source
    2.36
    sources
    2.28
     quoted
    2.16
     quotes
    2.16
     cited
    2.03
     Sources
    2.03
     quotations
    2.02
    Sources
    1.94
    source
    1.93
    Activations Density 0.073%

    No Known Activations