© 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. 138881
    Prev
    Next
    INDEX
    Explanations

    passport and travel documents

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

    travelled to

    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
    မ
    0.46
    บ
    0.43
    พวกเขา
    0.43
    ้
    0.43
    钢琴
    0.41
     আখ্যা
    0.41
     শা
    0.40
    บาท
    0.40
     Blvd
    0.39
     tweeting
    0.39
    POSITIVE LOGITS
     passport
    0.48
     паспорт
    0.48
    ustion
    0.47
    ೯
    0.46
     Europäischen
    0.46
     turista
    0.45
    airlines
    0.45
     hoher
    0.44
    oxine
    0.44
    民宿
    0.44
    Activations Density 0.002%

    No Known Activations