© 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. 39763
    Prev
    Next
    INDEX
    Explanations

    items with associated brands

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

    The neuron activates on mentions of proper names, brands, logos, and other trademarked or capitalized entities.

    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
    gisayar
    -1.21
     verschillen
    -1.16
     protože
    -1.10
     المعيار
    -1.09
     ktoré
    -1.09
    ILLY
    -1.05
    Beijo
    -1.05
     ktorá
    -1.03
    ajuku
    -1.02
    ほうがいい
    -1.02
    POSITIVE LOGITS
     logo
    1.48
     logos
    1.16
     their
    1.07
     prominent
    1.06
     at
    1.03
     branding
    1.03
    图案
    1.00
     flair
    0.99
    CommonModule
    0.98
    logo
    0.95
    Activations Density 0.033%

    No Known Activations