© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1374
    Prev
    Next
    INDEX
    Explanations

    my or my license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
     Numerous
    1.13
    ၏
    1.05
     Indicates
    1.05
     ይታ
    1.04
    
    1.04
     nedenle
    1.03
     genoemd
    1.03
     అనేక
    0.99
     preceding
    0.99
     elucidated
    0.98
    POSITIVE LOGITS
     my
    2.09
     আমার
    1.94
     minha
    1.90
    我的
    1.89
     myself
    1.85
    俺
    1.79
    我
    1.77
     আমি
    1.77
     мои
    1.74
     meine
    1.74
    Activations Density 0.266%

    No Known Activations