© 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. 16472
    Prev
    Next
    INDEX
    Explanations

    concepts and definitions

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

    relational prepositions across languages

    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
     composure
    0.43
    ס
    0.42
    拿着
    0.42
     composée
    0.39
    ス
    0.39
    चारिक
    0.39
    าร์
    0.39
     توجہ
    0.38
     pyaar
    0.38
    サイズの
    0.38
    POSITIVE LOGITS
     لدى
    0.88
    日本では
    0.86
     chez
    0.80
     بالنسبة
    0.79
     here
    0.78
     ở
    0.78
     здесь
    0.77
     bagi
    0.76
    在这里
    0.75
     عندنا
    0.74
    Activations Density 0.064%

    No Known Activations