© 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. 1337
    Prev
    Next
    INDEX
    Explanations

    The neuron is a content‐word noun detector, strongly activating on single nouns and proper nouns (e.g. website names, system components, locations) rather than on function words.

    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
    在其
    0.79
    在前
    0.78
    នៅក្នុង
    0.73
    在此
    0.69
    在了
    0.68
    ออกจาก
    0.68
    在该
    0.68
    在
    0.66
    在本
    0.66
    在这
    0.64
    POSITIVE LOGITS
     where
    1.43
    where
    1.23
     όπου
    1.23
     donde
    1.17
     где
    1.16
     hvor
    1.13
     où
    1.13
     حيث
    1.06
     gdzie
    1.03
     alongside
    1.02
    Activations Density 0.964%

    No Known Activations