© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8195
    Prev
    Next
    INDEX
    Explanations

    investment and return

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

    The main thing this neuron does is detect mentions of financial “rate of return” or interest‐rate expressions.

    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_31_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
     nomor
    0.62
    数値
    0.57
    數字
    0.57
    ೦
    0.55
     postérieure
    0.55
     perhitungan
    0.54
    เยี่ยม
    0.54
     něj
    0.53
     bilangan
    0.52
    始めた
    0.51
    POSITIVE LOGITS
     investments
    0.61
    erry
    0.59
     investing
    0.57
     invested
    0.57
    Delay
    0.57
     alternatives
    0.56
    rypto
    0.56
    舝
    0.56
     $>$
    0.55
     investment
    0.55
    Activations Density 0.001%

    No Known Activations