© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7765
    Prev
    Next
    INDEX
    Explanations

    press, column, USD

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

    The neuron chiefly detects numeric tokens—especially measurement values and other numbers (including floats).

    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
    Descrição
    0.74
    Tidak
    0.70
    Origen
    0.70
    شت
    0.69
    Эта
    0.68
    [
    0.68
     filled
    0.68
    𝑨
    0.68
     happier
    0.66
    Christopher
    0.66
    POSITIVE LOGITS
     पटेल
    0.82
     AMG
    0.82
     AMOLED
    0.79
     PAOK
    0.79
     vegetative
    0.76
     britt
    0.75
     Cox
    0.74
     legy
    0.74
     दैनिक
    0.73
     AWD
    0.73
    Activations Density 0.000%

    No Known Activations