© 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. 14359
    Prev
    Next
    INDEX
    Explanations

    code structures like lists, objects, and functions

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

    The neuron strongly activates on tokens that are numeric codes or identifiers (i.e. tokens containing digits).

    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
    onuclease
    0.67
    π
    0.60
     suppuration
    0.59
    oxyl
    0.59
    yl
    0.58
    r
    0.58
     oxidizing
    0.58
    n
    0.57
    ine
    0.57
    t
    0.57
    POSITIVE LOGITS
     pekerja
    0.74
     Themen
    0.73
    学院
    0.71
     finans
    0.71
     persiapan
    0.71
     mereka
    0.70
     asuntos
    0.70
     noticias
    0.70
     empresarios
    0.70
     Políticas
    0.69
    Activations Density 0.153%

    No Known Activations