© 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. 212
    Prev
    Next
    INDEX
    Explanations

    URLs and src attributes

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

    The neuron fires on tokens involved in specifying external resource URLs (e.g. CSS url(), HTML `src=` attributes, Vue.js `v-lazy` bindings to image URLs).

    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
     với
    -0.92
     것입니다
    -0.89
     lifespan
    -0.89
     Polskiej
    -0.86
    southeast
    -0.86
    entrums
    -0.86
    ক্ত
    -0.85
     autres
    -0.84
     welke
    -0.84
    INOS
    -0.84
    POSITIVE LOGITS
    çade
    1.06
     from
    1.05
    鲧
    1.04
    ﻻ
    0.99
     gewä
    0.92
    şil
    0.92
    倶楽部
    0.91
    sellor
    0.90
    殡
    0.90
     contending
    0.89
    Activations Density 0.001%

    No Known Activations