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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92329
    Prev
    Next
    INDEX
    Explanations

    navbar, nav, navigation

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

    The neuron is triggered by HTML markup tokens—especially the “<” character and the tag names that follow it.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    حت
    -0.87
     Lenz
    -0.79
    entiel
    -0.75
    ماس
    -0.73
     Endocrinology
    -0.73
    voja
    -0.72
    mocha
    -0.72
     perjury
    -0.71
    hierarchy
    -0.71
    phrine
    -0.71
    POSITIVE LOGITS
    navbar
    2.08
     Navbar
    2.05
     navbar
    2.00
    Navbar
    1.90
     NavBar
    1.84
    nav
    1.77
    NavBar
    1.74
    导航
    1.63
     nav
    1.60
     navigation
    1.59
    Activations Density 0.027%

    No Known Activations