© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63106
    Prev
    Next
    INDEX
    Explanations

    resort hotel vacation

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

    The neuron activates primarily on words and punctuation that appear in large, uppercase section headers or titles (e.g. “FEATURE: Breathless Resorts”), especially the colon that ends the heading.

    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
     Shakti
    -0.85
     uska
    -0.84
    ГУ
    -0.80
    地方
    -0.76
    mantel
    -0.75
     tarda
    -0.74
     entrepre
    -0.74
     mantel
    -0.73
    ebra
    -0.72
     moter
    -0.72
    POSITIVE LOGITS
     resort
    1.87
     resorts
    1.68
    resort
    1.37
     AI
    1.24
     Resort
    1.23
    Resort
    1.18
     vacation
    1.16
     Sandals
    1.16
     Resorts
    1.15
     hotel
    1.12
    Activations Density 0.023%

    No Known Activations