© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130759
    Prev
    Next
    INDEX
    Explanations

    prepositions of place, direction, or duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     レスト
    -1.74
    酲
    -1.68
     ストレッチ
    -1.62
    
    -1.62
     Certaines
    -1.52
    逺
    -1.51
    ♪♪
    -1.49
    ƾ
    -1.48
     arse
    -1.45
    洐
    -1.45
    POSITIVE LOGITS
     what
    1.62
     out
    1.62
     chief
    1.54
     fisuras
    1.53
     most
    1.53
     best
    1.52
     after
    1.50
     just
    1.49
     well
    1.49
     doing
    1.45
    Activations Density 0.074%

    No Known Activations