© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13585
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_16k_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
    ToRemove
    0.55
    י
    0.52
    শূন্য
    0.51
     in
    0.50
    Remove
    0.49
    u
    0.49
    สู่
    0.49
    ীর্ণ
    0.49
    ي
    0.48
            
    0.48
    POSITIVE LOGITS
    停止
    1.09
     dừng
    1.09
     stopped
    1.06
     stopping
    1.02
     Stopping
    1.02
    stopping
    1.01
     stop
    0.98
     останови
    0.98
    Stopping
    0.97
     останавли
    0.97
    Activations Density 0.138%

    No Known Activations