© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4403
    Prev
    Next
    INDEX
    Explanations

    This neuron detects commercial or promotional listing language, such as seller/product/service descriptions.

    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_24_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
    フル
    0.86
    Rets
    0.85
    ور
    0.82
     상당히
    0.79
     Chưa
    0.78
     könnten
    0.77
     ၁
    0.77
     excite
    0.76
     digress
    0.75
     imdb
    0.74
    POSITIVE LOGITS
    पालिका
    0.79
    𝗵
    0.72
    ist
    0.71
     chy
    0.70
    lama
    0.69
    lig
    0.68
    ai
    0.66
    ﻟ
    0.66
    ский
    0.65
    ayan
    0.65
    Activations Density 0.000%

    No Known Activations