© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13119
    Prev
    Next
    INDEX
    Explanations

    routes and navigation

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

    This neuron responds to React Router JSX elements and props, i.e. the `<Router>` and `<Route>` (and related) tags and their `component`/`history` attributes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     each
    -1.49
     regarding
    -1.27
     doua
    -1.27
    樓
    -1.25
     when
    -1.21
     from
    -1.21
     during
    -1.21
     emporio
    -1.21
     valoraciones
    -1.21
     jurk
    -1.20
    POSITIVE LOGITS
    ynchronously
    1.45
    cension
    1.38
    AfterViewInit
    1.26
    bestos
    1.23
    inine
    1.21
     ライト
    1.19
    vény
    1.19
    くらいで
    1.17
     chiffre
    1.16
     tungkol
    1.16
    Activations Density 0.134%

    No Known Activations