© 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. 5324
    Prev
    Next
    INDEX
    Explanations

    pensando en, resumo los

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

    The main thing this neuron does is detect numeric tokens—especially multi-digit numbers, decimals, and measurements—within the text.

    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
     
    1.16
     Russian
    1.07
     &
    0.98
    8
    0.97
     University
    0.95
     opposing
    0.93
    0
    0.91
    9
    0.89
    2
    0.89
     blood
    0.87
    POSITIVE LOGITS
    prueba
    1.98
     imprescindible
    1.92
    Además
    1.89
    productos
    1.89
    Algun
    1.88
     proyect
    1.87
    Espagne
    1.87
    mensaje
    1.85
     imprescind
    1.85
    Portada
    1.85
    Activations Density 0.628%

    No Known Activations