© 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. 1739
    Prev
    Next
    INDEX
    Explanations

    The neuron lights up on strongly positive evaluative language—especially emphatic praise and superlative descriptors.

    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
     proverbial
    0.81
    部份
    0.73
    所谓的
    0.68
     discretionary
    0.67
    、（
    0.67
    ・・・・
    0.66
       
    0.66
     "...
    0.66
    ,--
    0.64
     muß
    0.64
    POSITIVE LOGITS
     😍
    2.19
     ✨
    2.11
     ♡
    2.08
     ❤️
    2.06
     🙌
    2.03
    ☺️
    1.97
     ❤
    1.96
     💕
    1.96
     🥰
    1.95
     :)
    1.95
    Activations Density 0.440%

    No Known Activations