© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5295
    Prev
    Next
    INDEX
    Explanations

    screws and dimensions

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

    screws and threaded components

    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_53_width_65k_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
    韆
    0.51
    部門
    0.47
     vehemently
    0.47
    路線
    0.47
    潇
    0.46
    濁
    0.46
     लटका
    0.45
     materialistic
    0.44
    幀
    0.44
    簾
    0.44
    POSITIVE LOGITS
     threaded
    1.64
     screw
    1.58
    threaded
    1.45
     screws
    1.38
     Screw
    1.34
    screw
    1.33
    Screw
    1.31
     flange
    1.30
     screwing
    1.27
     threads
    1.26
    Activations Density 0.288%

    No Known Activations