© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1609
    Prev
    Next
    INDEX
    Explanations

    market growth and CAGR

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

    The neuron strongly activates on the formal metadata and numeric/statistical tokens found in market-research report excerpts (e.g. report titles, dates, page counts, data figures).

    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
    罵
    0.53
    を使う
    0.48
    使う
    0.47
    Girl
    0.45
     housework
    0.45
     ragazza
    0.43
    骂
    0.43
    日記
    0.43
    ff
    0.43
    IfNeeded
    0.42
    POSITIVE LOGITS
     mondiale
    0.54
     comprehensively
    0.51
     글로벌
    0.50
     시장
    0.50
    市场
    0.49
     mondial
    0.48
     comprehensive
    0.47
     especializado
    0.47
     selaku
    0.47
     बाजार
    0.47
    Activations Density 0.024%

    No Known Activations