© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 628
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on specialized technical and scientific terms (including chemical names, acronyms, and other domain‐specific jargon).

    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
     Bestellung
    0.44
    🤏
    0.43
    T
    0.41
     gute
    0.41
     filha
    0.40
    🤚
    0.40
     ಆದರೆ
    0.40
     hilfre
    0.40
     उनकी
    0.39
     dyslex
    0.39
    POSITIVE LOGITS
    と呼ばれる
    0.72
     consists
    0.69
     comprises
    0.69
     refers
    0.67
    是一种
    0.67
     differs
    0.66
    ®,
    0.61
    ®
    0.61
     originates
    0.60
     /ˈ
    0.59
    Activations Density 2.787%

    No Known Activations