© 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. 11199
    Prev
    Next
    INDEX
    Explanations

    investment

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

    The neuron strongly activates on mentions of monetary returns or investments (e.g., “investment,” “money”).

    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
    ълга
    0.80
    Cord
    0.79
    斯
    0.75
     للع
    0.74
    Univ
    0.71
     Че
    0.69
    Những
    0.69
    Miles
    0.68
    ആ
    0.68
    Suffix
    0.68
    POSITIVE LOGITS
     Enables
    0.77
     atthe
    0.71
     typos
    0.70
    ベリー
    0.69
    เดิม
    0.68
     typo
    0.68
     vertebr
    0.65
     clang
    0.65
    sthrough
    0.65
     neodymium
    0.65
    Activations Density 0.001%

    No Known Activations