© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13498
    Prev
    Next
    INDEX
    Explanations

    units, measurements, or dimensions

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

    The neuron strongly activates on quantitative or numeric expressions—counts, ratings, measurements, large numbers—anywhere the text presents statistics or figures.

    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_31_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
     rach
    0.75
     fizik
    0.74
     svare
    0.73
     baos
    0.72
     salon
    0.71
     \
    0.70
    guard
    0.70
    codile
    0.70
    yled
    0.68
     ido
    0.68
    POSITIVE LOGITS
     parvenir
    0.79
    ര്‍
    0.75
     вследствие
    0.73
     поради
    0.71
     recognizing
    0.69
    <unused10>
    0.68
    ிரிய
    0.68
    једина
    0.67
     elusive
    0.67
     accredited
    0.66
    Activations Density 0.000%

    No Known Activations