© 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. 107714
    Prev
    Next
    INDEX
    Explanations

    internet slang and acronyms

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

    The neuron strongly activates on short all-caps letter sequences (especially common internet/texting acronyms and initialisms).

    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
     racconto
    -0.99
    VERTIS
    -0.94
    اگر
    -0.93
     schermata
    -0.88
     għal
    -0.87
     mason
    -0.87
     Pamph
    -0.86
     レモン
    -0.86
    山东
    -0.86
    телям
    -0.85
    POSITIVE LOGITS
     What
    1.29
     Yes
    1.16
     Thank
    1.06
     hello
    1.05
     Hello
    1.04
     How
    1.03
     Oh
    1.01
     thank
    1.00
     yes
    0.98
     Please
    0.98
    Activations Density 0.037%

    No Known Activations