© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 8190
    Prev
    Next
    INDEX
    Explanations

    manufacturing process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cognitive
    0.64
     cognit
    0.62
     نظری
    0.59
     kript
    0.55
     Student
    0.54
     бібліоте
    0.53
    图书馆
    0.52
     😘
    0.52
     Studenten
    0.52
     pasaj
    0.52
    POSITIVE LOGITS
     manufacturing
    1.99
    manufacturing
    1.73
     factories
    1.70
     production
    1.68
    製造
    1.63
     manufacture
    1.61
    Manufacturing
    1.61
     Manufacturing
    1.57
     производство
    1.57
    生产
    1.50
    Activations Density 0.208%

    No Known Activations