© 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. 8349
    Prev
    Next
    INDEX
    Explanations

    including or arguments

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

    The neuron strongly activates on product‐listing or marketing headline tokens—e.g. brand and model names, app or item titles, prices, and other promotional jargon.

    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
    ,
    1.22
    ר
    1.15
    ى
    1.10
    1.09
    で
    1.07
    ной
    1.05
    )
    1.03
    .
    1.02
    cular
    0.99
    TING
    0.97
    POSITIVE LOGITS
     illetve
    1.65
     czyli
    1.52
     który
    1.51
     odnosno
    1.50
     whiche
    1.36
     което
    1.36
     اتارنا
    1.36
     vilket
    1.34
     einschließlich
    1.33
     ktoré
    1.32
    Activations Density 1.762%

    No Known Activations