© 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. 481
    Prev
    Next
    INDEX
    Explanations

    This neuron detects promotional call-to-action or disclaimer language—especially “if you loved this article and would like to receive more information” style subscription prompts and warranty-type statements.

    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
    steak
    0.29
    𝘨
    0.27
    चाकी
    0.27
    atre
    0.26
    diversity
    0.26
    𝘬
    0.26
    рие
    0.26
    𝘤
    0.26
    canoe
    0.25
    imed
    0.25
    POSITIVE LOGITS
     Sedangkan
    0.27
     Thats
    0.27
     Güzel
    0.26
     Setiap
    0.24
     waren
    0.24
     Miłos
    0.23
     MyBatis
    0.23
     lendemain
    0.23
     During
    0.23
     The
    0.23
    Activations Density 0.042%

    No Known Activations