© 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. 24-GEMMASCOPE-2-RES-16K
    7. 7147
    Prev
    Next
    INDEX
    Explanations

    steps before or after

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

    The neuron fires on tokens that mark or occur in numbered or enumerated list items (e.g. numbers, clause labels, list markers).

    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
    üedad
    1.05
    땔
    0.96
     способствует
    0.94
     enunciado
    0.93
     overland
    0.89
     deciduous
    0.89
     Woot
    0.89
     предоставля
    0.88
     intramuscular
    0.88
     agrarian
    0.88
    POSITIVE LOGITS
    اد
    0.94
    أ
    0.87
    و
    0.86
    ر
    0.84
    at
    0.83
    心
    0.78
    You
    0.75
    هو
    0.75
    ats
    0.74
    را
    0.74
    Activations Density 0.000%

    No Known Activations