© 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. 19571
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb or noun

    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
     with
    -2.77
     both
    -1.88
     that
    -1.82
     without
    -1.82
     you
    -1.69
     each
    -1.55
     while
    -1.55
     others
    -1.54
     before
    -1.51
     your
    -1.41
    POSITIVE LOGITS
     chaleco
    1.56
     tinha
    1.55
    olingo
    1.54
     REALLY
    1.52
    5
    1.48
    9
    1.45
    桧
    1.44
     estuche
    1.43
     rapporter
    1.42
    oncé
    1.38
    Activations Density 0.085%

    No Known Activations