© 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. 14210
    Prev
    Next
    INDEX
    Explanations

    chiefly acts

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

    The neuron is tuned to detect numeric values and statistical figures (i.e. tokens representing numbers or measurements).

    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
     subtracted
    0.75
     stopped
    0.71
     juries
    0.71
    mLogin
    0.70
    ختلف
    0.68
     invalidated
    0.68
    犀
    0.68
    גע
    0.68
    ToServer
    0.68
    Ⲩ
    0.66
    POSITIVE LOGITS
    ålet
    0.88
     yaşanan
    0.84
     dela
    0.82
     Harr
    0.78
    oyeva
    0.76
     Chaudhary
    0.76
    ringen
    0.75
     vergessen
    0.75
    ્ટ
    0.75
     functie
    0.73
    Activations Density 0.000%

    No Known Activations