© 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. 137162
    Prev
    Next
    INDEX
    Explanations

    travel and foreign places

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

    cultural immersion, different perspectives, foreign films

    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
     nieuwe
    0.44
    Logistic
    0.43
     nhàng
    0.42
     procent
    0.42
    投标人
    0.42
    нами
    0.41
    ంచెం
    0.41
    奈
    0.41
     normalen
    0.41
    وضوع
    0.40
    POSITIVE LOGITS
     embank
    0.44
     sightseeing
    0.42
     ailments
    0.42
     stints
    0.42
     ktorá
    0.41
     বন্যা
    0.40
     관광
    0.40
     시절
    0.40
    ǽ
    0.40
     tourist
    0.39
    Activations Density 0.000%

    No Known Activations