© 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. 33254
    Prev
    Next
    INDEX
    Explanations

    lodging and accommodation

    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
     quidem
    -0.85
    isPlaying
    -0.83
    vartis
    -0.81
     siedz
    -0.78
    multline
    -0.78
     malls
    -0.77
     khối
    -0.75
    醇
    -0.74
     reaction
    -0.74
     فريبيس
    -0.73
    POSITIVE LOGITS
     Airbnb
    1.65
     Bed
    1.59
     accommodation
    1.56
     guesthouse
    1.48
     bed
    1.48
     homestay
    1.44
     hostel
    1.39
     Pension
    1.38
     guest
    1.38
     Guest
    1.36
    Activations Density 0.032%

    No Known Activations