© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10788
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numbered section headings—specifically digit‐period markers like “2.” at the start of outline items.

    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_31_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
    ouc
    0.62
    夂
    0.59
    万
    0.58
    췄
    0.58
    тических
    0.56
    同学
    0.55
    ächlich
    0.54
    役
    0.54
    同學
    0.53
    citealt
    0.53
    POSITIVE LOGITS
     CONTRACT
    0.61
     εγκα
    0.60
     жү
    0.59
     Premier
    0.58
     化
    0.57
     Infrast
    0.57
     contract
    0.56
     infrastructure
    0.56
     एंटर
    0.55
     Console
    0.55
    Activations Density 0.000%

    No Known Activations