© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10497
    Prev
    Next
    INDEX
    Explanations

    names starting with N, Ni, or Nim

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

    Ni followed by word part

    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_40_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
    another
    0.54
     another
    0.46
     ANOTHER
    0.45
    餑
    0.41
    另一个
    0.41
    proper
    0.41
     altra
    0.40
     properly
    0.39
     மற்றொரு
    0.39
     otra
    0.38
    POSITIVE LOGITS
     نی
    0.50
     hí
    0.41
     meriye
    0.40
     Ни
    0.40
     Niv
    0.40
    újt
    0.38
     Either
    0.38
     Vav
    0.37
     니
    0.37
    ContentView
    0.36
    Activations Density 0.174%

    No Known Activations