© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14910
    Prev
    Next
    INDEX
    Explanations

    definitions and counts

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

    The neuron is activated by numeric tokens—especially explicit numbers, percentages, or decimal values indicating quantities.

    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
    но
    0.91
    于
    0.86
     fonds
    0.84
    Ant
    0.80
    Montserrat
    0.79
    ان
    0.78
    André
    0.78
    ODM
    0.78
    Hallo
    0.77
    ہ
    0.76
    POSITIVE LOGITS
     fateful
    0.87
     encroach
    0.86
     wavelength
    0.84
     gaseous
    0.79
     tainted
    0.77
     fatal
    0.77
    te
    0.76
     infar
    0.75
     ignited
    0.75
    line
    0.75
    Activations Density 0.000%

    No Known Activations