© 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. 20906
    Prev
    Next
    INDEX
    Explanations

    travel insurance and citizens abroad

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

    travel advisories and safety

    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
    轴
    0.51
    Plastic
    0.48
    锗
    0.45
    dropPanel
    0.44
    TableName
    0.44
    Stopping
    0.44
    键
    0.44
    뮐
    0.43
    小数
    0.43
    Clock
    0.43
    POSITIVE LOGITS
     consular
    1.05
     consulate
    0.97
     repatriation
    0.93
     embassy
    0.88
     Embassy
    0.86
     embassies
    0.84
     Consulate
    0.80
     overseas
    0.77
     repatri
    0.77
     diplomats
    0.76
    Activations Density 0.057%

    No Known Activations