© 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. 31-GEMMASCOPE-2-RES-16K
    7. 714
    Prev
    Next
    INDEX
    Explanations

    This neuron identifies quantitative details—numbers, measurements, and other metrics.

    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
     Specifies
    0.48
    Impl
    0.48
     TComponent
    0.46
     Serikat
    0.46
     কিরূপে
    0.46
     №
    0.45
     う
    0.44
     Ispol
    0.43
     নিশ্চয়
    0.43
     According
    0.42
    POSITIVE LOGITS
     tacos
    0.84
     whiskey
    0.74
     popcorn
    0.73
     taco
    0.73
     granola
    0.73
     biscuits
    0.72
    -/
    0.72
     lasagna
    0.72
     bluegrass
    0.72
     pizzas
    0.70
    Activations Density 3.052%

    No Known Activations