© 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. 25706
    Prev
    Next
    INDEX
    Explanations

    meta tags and titles

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

    This neuron fires on the literal “react-helmet” import (i.e. the tokens in the `import Helmet from 'react-helmet';` statement).

    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
     Needham
    -0.83
    贪
    -0.81
     trực
    -0.79
    dominal
    -0.79
     Burrows
    -0.78
    preuve
    -0.77
    issent
    -0.76
     Brust
    -0.73
     Graphical
    -0.73
    butyl
    -0.72
    POSITIVE LOGITS
     meta
    2.03
     SEO
    2.00
    meta
    1.81
     head
    1.81
     Meta
    1.77
    SEO
    1.66
    Meta
    1.58
     мета
    1.55
    Helmet
    1.52
    seo
    1.52
    Activations Density 0.066%

    No Known Activations