© 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. 5025
    Prev
    Next
    INDEX
    Explanations

    page, toy, table, confidential

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

    The neuron is keyed to commercial retail jargon, especially phrases advertising inexpensive or wholesale consumer products (e.g. “wholesale jerseys,” “cheap iPhone cases,” “Hermès replica handbags”).

    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
    𝑰
    0.86
    𝑫
    0.78
    𝑻
    0.78
    entlichen
    0.77
    یت
    0.73
     esso
    0.72
    Ked
    0.71
     енер
    0.71
    ς
    0.70
    𝐊
    0.70
    POSITIVE LOGITS
    grim
    0.82
    problems
    0.80
    and
    0.79
    up
    0.77
     समस्याओं
    0.75
    ight
    0.73
    Problems
    0.73
    ucked
    0.71
     हितों
    0.71
    upp
    0.71
    Activations Density 0.002%

    No Known Activations