© 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. 13690
    Prev
    Next
    INDEX
    Explanations

    current trends and popularity

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

    The neuron responds strongly to multiword “trendy” phenomena or niche topics—e.g. kombucha beverages, found-footage horror movies, paranormal activity, spin-class fitness, etc.—i.e. names of specific cultural/fad phenomena.

    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
     underrated
    -1.09
     nakalista
    -1.04
    ̹
    -1.02
     roleId
    -0.98
    puter
    -0.96
    bardziej
    -0.93
    ecommerce
    -0.93
    choenen
    -0.93
    誨
    -0.92
     getById
    -0.91
    POSITIVE LOGITS
     lately
    1.38
     trendy
    1.35
     craze
    1.30
     recently
    1.24
     популяр
    1.19
     everyone
    1.18
     ormai
    1.18
    Trend
    1.17
     trend
    1.09
     popularity
    1.09
    Activations Density 0.204%

    No Known Activations