© 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. 8441
    Prev
    Next
    INDEX
    Explanations

    automation, pharmaceutical, culture, cyber, Transformer, folklore, training, shopping, advertising

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

    The neuron fires strongly on nouns naming structured “offerings” or “services” (e.g. tourism packages, exhibitions, cultural exports, treatments) in a business or institutional context.

    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
    ড
    1.05
     আমায়
    0.93
    立刻
    0.92
    大约
    0.92
     Thousands
    0.87
     तपाईं
    0.87
    伱
    0.86
    প্ট
    0.85
     你
    0.84
     পালিয়ে
    0.82
    POSITIVE LOGITS
     managerial
    1.18
     entrepreneurial
    1.17
    に係る
    1.12
     sociocultural
    1.09
     intercultural
    1.09
     intangible
    1.05
     interpersonal
    1.05
     isomorphism
    1.04
     constituyen
    1.02
     organizacional
    1.02
    Activations Density 2.147%

    No Known Activations