© 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-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 565
    Prev
    Next
    INDEX
    Explanations

    web links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_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
    <0xF3>
    1.06
     покри
    0.96
    Кли
    0.92
     світу
    0.90
    ของเรา
    0.88
    ™
    0.87
     epochs
    0.86
     ✓
    0.85
    cycles
    0.85
    รู
    0.85
    POSITIVE LOGITS
     Department
    1.77
     Ministry
    1.72
     وزارة
    1.69
     pemerintah
    1.62
     Pemerintah
    1.59
     Commission
    1.58
     government
    1.57
     Kementerian
    1.55
     Consejo
    1.52
     parliamentary
    1.51
    Activations Density 1.239%

    No Known Activations