© 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. 45420
    Prev
    Next
    INDEX
    Explanations

    citation markers like [@

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

    The neuron detects in-text citation markers (e.g. superscripted reference numbers or bracketed reference IDs).

    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
    .(*
    -0.79
    枭
    -0.75
    endios
    -0.73
     鐵
    -0.71
     Wern
    -0.71
    Erich
    -0.70
    润
    -0.70
     lundi
    -0.70
     ANDRE
    -0.69
    opheles
    -0.68
    POSITIVE LOGITS
     [
    0.93
    reference
    0.82
    geleitet
    0.77
     ngọc
    0.77
    FlatList
    0.76
     frequentemente
    0.75
     ليست
    0.75
    nis
    0.75
    ביב
    0.75
    see
    0.74
    Activations Density 0.034%

    No Known Activations