© 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. 10-GEMMASCOPE-RES-131K
    7. 83835
    Prev
    Next
    INDEX
    Explanations

    hotel names and brands

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

    This neuron activates on hotel or resort brand names (e.g., Marriott, Sheraton, Hilton, Radisson, etc.).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Também
    -1.52
     компонентов
    -1.52
    y
    -1.51
    骉
    -1.51
    update
    -1.48
    appro
    -1.48
    ity
    -1.46
    agt
    -1.39
     charming
    -1.39
    vities
    -1.38
    POSITIVE LOGITS
     hidupnya
    1.41
    schuhe
    1.40
     händer
    1.30
    Salu
    1.30
     USSR
    1.30
     nifer
    1.27
     τοῦ
    1.27
    França
    1.27
    matem
    1.26
    Coff
    1.25
    Activations Density 0.011%

    No Known Activations