© 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. 12966
    Prev
    Next
    INDEX
    Explanations

    Millennials, fintech, equity

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

    The main thing this neuron does is detect proper names and named entities (e.g. specific people, places, brands, and other capitalized terms).

    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
     সম্বন্ধে
    1.00
    LensFlare
    0.95
    ARDS
    0.94
    WindowTitle
    0.91
     പറയുന്നു
    0.86
    AsyncKeyState
    0.86
    ».
    0.86
    ﹕
    0.86
    RestorePolicy
    0.82
    http
    0.82
    POSITIVE LOGITS
     PFAS
    1.39
     Esports
    1.15
     Fintech
    1.12
     ESG
    1.11
     millennials
    1.11
     Millennials
    1.09
     unapolog
    1.09
     fintech
    1.06
     Biden
    1.05
     DeFi
    1.05
    Activations Density 16.379%

    No Known Activations