© 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. 7160
    Prev
    Next
    INDEX
    Explanations

    text expansion

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

    The neuron is keyed to numeric expressions—digits, percentages, and other explicit quantity tokens.

    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
    ماً
    0.65
     mocy
    0.65
     му
    0.64
    ↵
    0.62
    宪
    0.62
     محدود
    0.61
     ム
    0.57
    рец
    0.57
    起き
    0.57
     مارت
    0.57
    POSITIVE LOGITS
    Ě
    0.89
    Nano
    0.89
    ULATIONS
    0.88
    List
    0.88
    EditText
    0.88
    LL
    0.84
    Nan
    0.84
     Lleg
    0.83
     nanofibers
    0.82
    Ā
    0.82
    Activations Density 0.000%

    No Known Activations