© 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. 10947
    Prev
    Next
    INDEX
    Explanations

    multilingual text snippets

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

    The neuron is firing on the main content words—especially nouns and other topic‐carrying terms—rather than on function words.

    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
     Gnade
    -1.00
     chris
    -1.00
     XXXV
    -0.96
    ⽀
    -0.95
     hh
    -0.94
     '"
    -0.93
    ઃ
    -0.93
    LITER
    -0.93
    を行い
    -0.93
     forties
    -0.93
    POSITIVE LOGITS
    問題
    1.19
    适合
    1.05
     から
    1.04
    נוּ
    1.02
    هنگ
    1.01
    അ
    1.01
     their
    1.00
    ᴀ
    0.97
    週末
    0.97
    唞
    0.97
    Activations Density 0.054%

    No Known Activations