© 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. 34-GEMMASCOPE-RES-131K
    7. 83801
    Prev
    Next
    INDEX
    Explanations

    hotel amenities and services

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    }$}
    -0.81
     Koch
    -0.78
    椽
    -0.75
     toilets
    -0.73
     McDonald
    -0.72
    backgroundImage
    -0.72
    VAO
    -0.71
    icza
    -0.71
     tri
    -0.71
    śl
    -0.69
    POSITIVE LOGITS
     minibar
    1.66
     room
    1.19
     complimentary
    1.13
     daily
    1.12
     tray
    1.09
     stocked
    0.99
     wake
    0.96
     minib
    0.94
     Movies
    0.94
     flask
    0.94
    Activations Density 0.008%

    No Known Activations