© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57189
    Prev
    Next
    INDEX
    Explanations

    scraping and removal

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

    The neuron fires on past-tense action words (especially procedural verbs ending in –ed) describing experimental or manufacturing steps.

    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
    нение
    -0.86
    Einstein
    -0.75
     wreath
    -0.74
     Übersetzungen
    -0.72
     Jara
    -0.71
    gpg
    -0.69
     спать
    -0.69
     cous
    -0.68
    tigkeits
    -0.68
    ーマ
    -0.67
    POSITIVE LOGITS
     scraping
    3.27
     scraper
    3.20
     scrape
    3.14
     Scra
    3.06
     scraped
    2.92
    Scra
    2.70
    scraper
    2.39
    scrape
    2.11
     scra
    2.06
    刮
    2.00
    Activations Density 0.043%

    No Known Activations