© 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. 4582
    Prev
    Next
    INDEX
    Explanations

    numbers or ranges

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

    This neuron activates on numeric tokens—especially quantities and measurements (e.g. numbers, decimal values).

    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
    the
    0.68
    0.67
    s
    0.65
     the
    0.64
     is
    0.62
     with
    0.61
    :
    0.60
    /
    0.58
    L
    0.57
    R
    0.55
    POSITIVE LOGITS
     vài
    0.93
     кілька
    0.84
    数十
    0.80
    十几
    0.80
     nekoliko
    0.79
     câteva
    0.79
     몇
    0.78
     няколко
    0.77
     několik
    0.76
     десятки
    0.75
    Activations Density 0.268%

    No Known Activations