© 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. 13728
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

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

    noun followed by preposition

    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
     მათი
    0.40
     นอกจาก
    0.38
     постоян
    0.37
    킁
    0.37
    他にも
    0.36
    来的
    0.36
    edent
    0.36
     প্রতিরোধের
    0.36
    测
    0.36
     يلا
    0.35
    POSITIVE LOGITS
     using
    0.77
     at
    0.76
     tại
    0.76
     through
    0.75
     katika
    0.75
     in
    0.74
     on
    0.74
     via
    0.72
     trên
    0.72
     în
    0.71
    Activations Density 0.030%

    No Known Activations