© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10190
    Prev
    Next
    INDEX
    Explanations

    lock and related phrases

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

    lock tables

    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_40_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
    戝
    0.42
    CLOSE
    0.42
    closing
    0.40
    ванням
    0.39
    Close
    0.39
     cio
    0.39
    开
    0.38
     chick
    0.38
    臨時
    0.38
    )$\
    0.38
    POSITIVE LOGITS
     lock
    1.37
     Lock
    1.29
     LOCK
    1.27
     locking
    1.25
     locks
    1.21
    Lock
    1.17
     लॉक
    1.16
     Locking
    1.16
    lock
    1.16
     locked
    1.13
    Activations Density 0.062%

    No Known Activations