© 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. 35872
    Prev
    Next
    INDEX
    Explanations

    Roman numerals or list item markers

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

    The neuron fires on document section or list item labels—specifically on standalone Roman numerals (I, II, III, etc.) and similar numeric heading 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_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
    定価
    -1.33
     kabát
    -1.28
    まさかの
    -1.27
     musíte
    -1.26
     quí
    -1.23
    の方に
    -1.23
    おわりに
    -1.22
     bych
    -1.21
     dinoss
    -1.20
     histó
    -1.19
    POSITIVE LOGITS
    i
    1.17
    主要
    1.07
     numerous
    1.05
    si
    1.02
    ’
    1.01
    l
    1.00
     is
    1.00
    u
    1.00
    0.99
     hippie
    0.98
    Activations Density 0.006%

    No Known Activations