© 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. 10682
    Prev
    Next
    INDEX
    Explanations

    hotel and flight deals

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

    travel comparison and booking

    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
     মি
    0.49
     KU
    0.46
     NFT
    0.44
     FAN
    0.43
     Population
    0.43
     KNN
    0.42
     Shirley
    0.42
     X
    0.41
     Organ
    0.40
     Anal
    0.40
    POSITIVE LOGITS
    hotels
    0.50
    机票
    0.47
    ufthansa
    0.46
    deals
    0.46
    means
    0.46
    оте
    0.45
    再來
    0.45
    hotel
    0.44
    וט
    0.44
    飯店
    0.44
    Activations Density 0.013%

    No Known Activations