© 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. 10470
    Prev
    Next
    INDEX
    Explanations

    economic and policy terms

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

    The neuron responds strongly to content words naming policy, economic, or infrastructure topics (e.g. immigration, public spending, electricity, mortgage interest, trade, traffic).

    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
    तियाँ
    0.64
    /
    0.63
    Ꮂ
    0.62
     இருப்பினும்
    0.61
     ഗെയി
    0.60
    ®.
    0.59
     necessitates
    0.58
     সম্বন্ধে
    0.58
     &/
    0.58
    liness
    0.57
    POSITIVE LOGITS
     staffers
    0.59
    ूल
    0.58
     jailed
    0.57
     رون
    0.54
     COULD
    0.54
     miR
    0.53
     Bolsonaro
    0.53
    ሱን
    0.53
     prosecutors
    0.52
     metadata
    0.52
    Activations Density 0.134%

    No Known Activations