© 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. 22-GEMMASCOPE-RES-131K
    7. 40028
    Prev
    Next
    INDEX
    Explanations

    digital platforms

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

    The neuron is sensitive to names of online platforms, websites, and digital service brands.

    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
    citroen
    -1.17
    uniqlo
    -1.16
     картофе
    -1.15
     Pharisees
    -1.13
    ਆ
    -1.13
    鎵
    -1.12
     cesta
    -1.09
    際に
    -1.09
    ிரு
    -1.09
    基本上
    -1.08
    POSITIVE LOGITS
     platform
    1.44
     seção
    1.20
     account
    1.17
    platform
    1.11
     STYLES
    1.09
    <bos>
    1.08
     operação
    1.08
    を与える
    1.06
    での
    1.05
    を与
    1.05
    Activations Density 0.124%

    No Known Activations