© 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. 77292
    Prev
    Next
    INDEX
    Explanations

    celebrations, vacations, and special occasions

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

    voting and social events

    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
    否
    0.44
     weiteren
    0.43
     Recherche
    0.42
    fetch
    0.41
    Since
    0.41
    无比
    0.41
    кор
    0.40
    الية
    0.40
    ط
    0.40
    ρευ
    0.40
    POSITIVE LOGITS
     booths
    0.53
     বন্ধুত্ব
    0.50
     হানাদার
    0.49
     εκεί
    0.48
     celebrations
    0.48
     pizzeria
    0.47
     extravaganza
    0.47
    棧
    0.46
     plantings
    0.46
     vacations
    0.46
    Activations Density 0.001%

    No Known Activations