© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108942
    Prev
    Next
    INDEX
    Explanations

    hotel amenities

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

    The neuron strongly activates on capitalized multi‐word names—especially place and hotel names or other proper nouns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     środow
    -0.84
    燜
    -0.84
    
    -0.81
    ﺶ
    -0.80
     deserto
    -0.80
     santuario
    -0.79
     robusto
    -0.79
    cafe
    -0.79
    ộm
    -0.79
    numericUpDown
    -0.79
    POSITIVE LOGITS
     wellness
    1.60
     Wellness
    1.24
     концеп
    1.15
     concept
    1.15
     Concept
    1.13
     wellbeing
    1.08
     SPA
    1.08
    Concept
    1.03
     VIP
    1.03
     golf
    1.03
    Activations Density 0.023%

    No Known Activations