© 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. 39326
    Prev
    Next
    INDEX
    Explanations

    adjectives preceding specific names

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

    The neuron sharply responds to standalone capitalized words that are the names or titles of entities—e.g. bands, venues, labels, events, or other proper-noun headings.

    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
     sirena
    -1.77
     lanterna
    -1.77
    
    -1.76
     interi
    -1.75
     gratuit
    -1.75
     nobili
    -1.74
     asoci
    -1.65
     alfabe
    -1.63
     asisten
    -1.63
     vola
    -1.62
    POSITIVE LOGITS
     That
    2.77
     There
    2.47
     Those
    2.08
     Only
    2.06
     They
    2.03
     The
    2.03
     Some
    2.00
     However
    2.00
     Since
    1.98
     For
    1.97
    Activations Density 0.071%

    No Known Activations