© 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. 79846
    Prev
    Next
    INDEX
    Explanations

    classic, vintage, traditional

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

    The neuron fires on words and phrases that evoke vintage or “old-school” style or nostalgia.

    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
     등록
    -1.20
     reseñas
    -1.18
    詬
    -1.14
     nowa
    -1.08
     soportar
    -1.04
     soñar
    -1.00
     traducciones
    -1.00
    ַּ
    -0.99
     conflictos
    -0.98
     diseñar
    -0.97
    POSITIVE LOGITS
     old
    1.65
     retro
    1.50
     traditional
    1.48
     тради
    1.27
     tradisional
    1.26
     nostalgia
    1.25
     tradicional
    1.23
     classic
    1.22
     like
    1.22
    traditional
    1.21
    Activations Density 0.038%

    No Known Activations