© 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. 870
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by specific nouns

    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
     oogen
    -1.44
     défis
    -1.44
     planètes
    -1.42
     sélections
    -1.41
     centaines
    -1.40
     réunions
    -1.37
    躥
    -1.37
    INDOW
    -1.37
     dirit
    -1.34
     onze
    -1.33
    POSITIVE LOGITS
     of
    1.85
     in
    1.61
     first
    1.55
     on
    1.55
     the
    1.53
     until
    1.45
     at
    1.41
     that
    1.41
     by
    1.38
     In
    1.37
    Activations Density 0.100%

    No Known Activations