© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10482
    Prev
    Next
    INDEX
    Explanations

    outings and trips

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    静
    0.45
     música
    0.42
     музыки
    0.41
     musique
    0.41
     hostel
    0.40
    قط
    0.40
     Hostel
    0.40
    靜
    0.40
    тельстве
    0.40
     sante
    0.39
    POSITIVE LOGITS
     outings
    1.44
     outing
    1.35
    外出
    1.32
    出门
    1.12
     trips
    1.11
     Trips
    1.04
     excursions
    0.94
     excursion
    0.89
    出去
    0.88
     trip
    0.87
    Activations Density 0.124%

    No Known Activations