© 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. 16016
    Prev
    Next
    INDEX
    Explanations

    conditional logic and programming constructs

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

    This neuron activates on floating‐point numeric tokens (numbers with decimal points).

    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
     summarizes
    0.77
     proposes
    0.76
     divides
    0.73
     approximates
    0.73
    落实
    0.72
     strengthens
    0.71
    鸦
    0.70
     incorporates
    0.67
    提出了
    0.67
     góp
    0.66
    POSITIVE LOGITS
     э
    0.94
     Возможно
    0.89
     gevoel
    0.88
     вариантов
    0.88
     эту
    0.86
     voglio
    0.85
     laufen
    0.85
     denk
    0.84
     estaban
    0.84
     Filme
    0.82
    Activations Density 0.000%

    No Known Activations