© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84147
    Prev
    Next
    INDEX
    Explanations

    linking words

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

    This neuron fires on code tokens that introduce or reference links/routes (e.g. link, Link, ui-sref, router, href).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    艫
    -1.17
     xadrez
    -1.08
     básicos
    -1.04
    投稿日
    -1.03
     navideña
    -1.02
    出来了
    -1.01
    ApiController
    -1.01
    انتهای
    -0.99
     suí
    -0.99
     vient
    -0.98
    POSITIVE LOGITS
     echten
    1.05
    september
    1.05
     bếp
    1.01
    *);
    1.01
     to
    0.97
    共に
    0.96
     geringen
    0.95
     ähnlichen
    0.92
    requency
    0.90
    ا
    0.90
    Activations Density 0.001%

    No Known Activations