© 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. 11072
    Prev
    Next
    INDEX
    Explanations

    operators and symbols

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

    The neuron consistently fires on numeric tokens representing measurements or statistics—especially decimal numbers and numeric fractions.

    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
     Litigation
    0.84
     Growers
    0.82
     afferma
    0.82
    ℞
    0.82
    ateurs
    0.81
     Modem
    0.80
    ুখী
    0.78
    都市
    0.78
     incess
    0.77
    usakan
    0.75
    POSITIVE LOGITS
    Aub
    0.79
     туда
    0.70
     bire
    0.69
    c
    0.69
     njemu
    0.68
     pared
    0.68
    ﺎ
    0.68
     всем
    0.67
     Сергея
    0.67
     geranium
    0.66
    Activations Density 0.000%

    No Known Activations