© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6716
    Prev
    Next
    INDEX
    Explanations

    This neuron detects list-item or section headings—i.e. single-word topical labels like “Budget,” “Features,” “Reviews,” “Brand,” or “Cost” that introduce bullet points or subsections.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     शब्दा
    0.55
     resulted
    0.54
     kinase
    0.54
     (?)
    0.54
     recital
    0.53
     À
    0.53
     Xmas
    0.52
     AND
    0.52
     termination
    0.51
     deletion
    0.51
    POSITIVE LOGITS
    是一位
    0.60
    เขต
    0.58
    することができます
    0.57
    ете
    0.57
    いは
    0.57
    \[
    0.56
     있는데요
    0.55
    占
    0.55
    漫画
    0.54
    мери
    0.54
    Activations Density 0.002%

    No Known Activations