© 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. 8702
    Prev
    Next
    INDEX
    Explanations

    numbers and number words

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

    The neuron detects explicit numeric quantities (numbers, often with units or counts).

    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
     حوالي
    0.68
     約
    0.66
    GraphQl
    0.66
    半年
    0.64
    約
    0.63
    상
    0.63
     சுமார்
    0.62
     가게
    0.61
    शनी
    0.61
     몇
    0.60
    POSITIVE LOGITS
     consecutive
    0.77
     vezes
    0.71
    fold
    0.69
     consecut
    0.66
     veces
    0.65
     unità
    0.64
     puluh
    0.62
    жды
    0.62
     consecutivos
    0.61
     случаев
    0.60
    Activations Density 0.653%

    No Known Activations