© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13585
    Prev
    Next
    INDEX
    Explanations

    stop by, stop reading, stop hiding

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

    actions of stopping

    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_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
     in
    0.64
            
    0.57
    ע
    0.54
    ן
    0.52
     açısından
    0.51
    י
    0.51
    สุขภาพ
    0.51
     away
    0.50
    פ
    0.48
     fidel
    0.48
    POSITIVE LOGITS
     dừng
    1.07
     Stopping
    1.07
     Stopped
    1.06
    stopped
    1.05
    停止
    1.05
    stopping
    1.05
     stopped
    1.04
    止
    0.99
     останови
    0.98
     Stop
    0.97
    Activations Density 0.202%

    No Known Activations