© 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. 1912
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric expressions—especially percentage figures and other numerical data.

    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
    ष्टिक
    0.64
    reathe
    0.64
    Timing
    0.63
    不容易
    0.63
    /(:
    0.62
    Calcium
    0.61
    Wellness
    0.61
    Racing
    0.61
    不易
    0.59
    Theta
    0.59
    POSITIVE LOGITS
     total
    1.34
     population
    1.23
     ukup
    1.13
     toplam
    1.11
     totales
    1.07
     totale
    1.06
     कुल
    1.05
     households
    1.03
     surveyed
    1.02
    总
    1.01
    Activations Density 0.451%

    No Known Activations