© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123713
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by articles

    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
     réponses
    -1.55
     étanche
    -1.52
     eventuell
    -1.47
     cueva
    -1.46
    ▃▃
    -1.44
     résultats
    -1.43
     Metode
    -1.42
     Projektu
    -1.41
    をご覧
    -1.38
    ーーーー
    -1.38
    POSITIVE LOGITS
     for
    1.94
     of
    1.88
     in
    1.82
     if
    1.63
     at
    1.59
    ↵↵↵
    1.50
    ↵↵↵↵
    1.43
     have
    1.42
     based
    1.40
    ?
    1.39
    Activations Density 0.399%

    No Known Activations