© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4984
    Prev
    Next
    INDEX
    Explanations

    The neuron detects comparative and superlative marketing claims—phrases that emphasize something as the “cheapest,” “leading,” “no other can match,” “most,” etc.

    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
     энерги
    0.68
    وبت
    0.67
    বর্তন
    0.66
    აწილ
    0.66
    🔢
    0.65
     энергии
    0.64
    㴌
    0.64
     "@{
    0.63
    ベーション
    0.63
    OPLE
    0.63
    POSITIVE LOGITS
     competitors
    1.12
     konkuren
    1.07
     other
    1.05
     competitor
    1.03
     comparable
    1.00
     rivals
    1.00
     vendors
    0.99
     overpriced
    0.97
     compar
    0.94
     elsewhere
    0.93
    Activations Density 1.202%

    No Known Activations