© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1495
    Prev
    Next
    INDEX
    Explanations

    travelers' stays or bookings

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

    travel style and interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ઘટ
    0.47
     шриф
    0.46
    拦截
    0.45
     мозга
    0.45
    环境变量
    0.43
    新
    0.43
    Environ
    0.43
    涡
    0.43
    quả
    0.42
    Environment
    0.42
    POSITIVE LOGITS
     travelers
    0.74
     travellers
    0.73
     travelling
    0.64
     tourists
    0.64
     luggage
    0.63
     visitors
    0.62
     traveling
    0.62
     turistas
    0.62
     temporary
    0.62
     traveller
    0.62
    Activations Density 0.076%

    No Known Activations