© 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. 107882
    Prev
    Next
    INDEX
    Explanations

    hotel services or features

    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
     villas
    -0.92
     villa
    -0.90
     sunscreen
    -0.86
    别墅
    -0.85
    },{
    -0.82
    راعة
    -0.80
    abinieri
    -0.80
     vč
    -0.78
    SceneManagement
    -0.77
    cai
    -0.76
    POSITIVE LOGITS
     hotel
    1.62
     breakfast
    1.41
     Hotel
    1.09
     reception
    1.09
    Hotel
    1.01
    hotel
    0.98
     lobby
    0.97
     Ibis
    0.96
     conference
    0.96
     parking
    0.95
    Activations Density 0.022%

    No Known Activations