© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3432
    Prev
    Next
    INDEX
    Explanations

    hotel or resort names

    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
    Negative Logits
     pursuing
    -0.91
     Pediat
    -0.88
    Tenant
    -0.79
     predicted
    -0.78
     visar
    -0.76
     okrę
    -0.75
     ہے۔
    -0.75
     Distrito
    -0.75
     obszar
    -0.75
     paired
    -0.74
    POSITIVE LOGITS
     hotel
    2.14
     Hotel
    2.03
    hotel
    1.59
    Hotel
    1.58
     resort
    1.43
     Resort
    1.41
     hotels
    1.34
    hôtel
    1.27
     HOTEL
    1.26
    otel
    1.21
    Activations Density 0.026%

    No Known Activations