© 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. 1918
    Prev
    Next
    INDEX
    Explanations

    division operation

    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
     mercure
    1.05
    賴
    1.05
     యా
    0.99
     തേ
    0.96
    赖
    0.95
     Mercury
    0.90
    cury
    0.90
    Mercury
    0.89
    害
    0.89
     Haynes
    0.89
    POSITIVE LOGITS
     divide
    3.72
     split
    3.71
     divided
    3.70
     division
    3.64
     divides
    3.55
     dividing
    3.52
     divisions
    3.52
     splits
    3.47
     dividido
    3.45
    divided
    3.43
    Activations Density 0.984%

    No Known Activations