© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 35474
    Prev
    Next
    INDEX
    Explanations

    manufacturing and woodworking

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

    record lathe woodworking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    Bollywood
    0.63
    shit
    0.62
     Naruto
    0.60
     Goku
    0.59
    Anime
    0.59
    fuck
    0.57
     Sasuke
    0.57
    👾
    0.57
    wtf
    0.56
     shit
    0.56
    POSITIVE LOGITS
     lathe
    0.71
     manufacturing
    0.70
     woodworking
    0.68
     hickory
    0.65
     manufacture
    0.63
     lathes
    0.61
     wood
    0.60
     manufacturers
    0.60
     cellulose
    0.59
     manuf
    0.59
    Activations Density 0.083%

    No Known Activations