© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9081
    Prev
    Next
    INDEX
    Explanations

    artists and cultural terms in multiple languages

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

    The neuron is tuned to pick up on marketing-style or business-related buzzwords and jargon (e.g. “organic,” “inspire,” “community,” “visibility,” “participate,” 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
     COVID
    0.85
     Biden
    0.84
     covid
    0.73
     ณ
    0.72
    ‼️
    0.69
     ২০২৩
    0.68
     Omicron
    0.66
     Covid
    0.65
     PFAS
    0.64
    🤭
    0.64
    POSITIVE LOGITS
    を使った
    0.85
    культур
    0.82
    rianças
    0.80
    artists
    0.79
     فرهنگی
    0.78
    riters
    0.77
    各种
    0.75
     künstler
    0.73
    Artists
    0.71
    を作る
    0.71
    Activations Density 0.083%

    No Known Activations