© 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. 5724
    Prev
    Next
    INDEX
    Explanations

    train traveling at

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron specializes in spotting promotional or “advertising” style language—phrases like offers, guides, product names, and calls to action.

    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
    濱
    0.77
     parton
    0.75
     khái
    0.73
     pictorial
    0.71
     PDPN
    0.70
    LOAD
    0.70
     superconduct
    0.70
    FIX
    0.69
     bimod
    0.69
     viewership
    0.68
    POSITIVE LOGITS
    était
    0.80
    osin
    0.80
     मध्य
    0.79
    ripción
    0.73
    église
    0.73
    溝
    0.73
    rive
    0.72
    atmosphere
    0.72
    ovski
    0.71
    oor
    0.70
    Activations Density 0.001%

    No Known Activations