© 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. 65364
    Prev
    Next
    INDEX
    Explanations

    academic citations or footnotes

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

    The neuron fires on isolated asterisk markers (e.g. “*” or “.*”) that mark footnotes or section breaks.

    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
     UIS
    -0.82
    وائد
    -0.80
    𝜃
    -0.79
    れました
    -0.79
    ceiling
    -0.77
    subcategory
    -0.77
    les
    -0.77
    ץ
    -0.76
     Đình
    -0.74
    lover
    -0.73
    POSITIVE LOGITS
    ⁾
    1.13
     笔
    0.88
     sabid
    0.87
     انواع
    0.85
     (*
    0.85
     hivat
    0.85
     скажу
    0.84
     appendix
    0.84
    簡単に
    0.84
     footnote
    0.82
    Activations Density 0.086%

    No Known Activations