© 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. 8807
    Prev
    Next
    INDEX
    Explanations

    engineer, engineering, technical

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

    The main thing this neuron does is detect engineering and technical terminology, i.e. mentions of engineering disciplines, technical systems, and related concepts.

    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
    n
    0.88
    s
    0.88
     welcoming
    0.80
     prosec
    0.77
    ociation
    0.75
     hust
    0.73
    وف
    0.72
     UP
    0.72
    א
    0.71
     Map
    0.70
    POSITIVE LOGITS
     ENGINEERING
    1.19
    🔩
    1.17
     इंजीनियरिंग
    1.16
     industriales
    1.16
     engineer
    1.09
     Engineering
    1.09
    Engineering
    1.09
     ingeniería
    1.08
    Тех
    1.08
     ENGINEERS
    1.05
    Activations Density 0.127%

    No Known Activations