© 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. 130623
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on standalone Roman numerals used as section or list headings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    true, false, USA

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    rapid
    -0.96
    圃
    -0.84
    এ
    -0.84
    Rapid
    -0.83
    GroupLayout
    -0.83
    🇺
    -0.82
    otex
    -0.81
    Hy
    -0.80
    тит
    -0.80
    媚
    -0.80
    POSITIVE LOGITS
    ؋
    0.90
     respectively
    0.87
     distintas
    0.85
    Biografie
    0.80
    ͌
    0.80
    čenie
    0.79
    izoen
    0.79
    ệc
    0.79
     espectaculares
    0.79
    ございます
    0.79
    Activations Density 0.028%

    No Known Activations