© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2700
    Prev
    Next
    INDEX
    Explanations

    footnote and citation markers

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

    The neuron detects reference markers and footnote/citation annotations (e.g., bracketed superscripts, “fn” tags, and similar inline citation markers).

    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
    Externí
    -1.03
    bbies
    -0.80
     básico
    -0.76
    Enlaces
    -0.75
     preguntó
    -0.71
    矍
    -0.70
    giatan
    -0.70
     monarch
    -0.69
    Enllaces
    -0.69
    šina
    -0.68
    POSITIVE LOGITS
     footnotes
    4.03
     footnote
    4.03
     foot
    3.59
    Footnotes
    3.31
     Foot
    3.28
    footnote
    3.19
     Footnote
    3.08
     FOOT
    3.02
    foot
    2.83
    Footnote
    2.83
    Activations Density 0.111%

    No Known Activations