© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102761
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings after punctuation

    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
     نیز
    -1.91
     mentale
    -1.57
    Ayrıca
    -1.55
     fatale
    -1.54
    joyed
    -1.52
     adal
    -1.52
     robuste
    -1.51
     jari
    -1.45
     имена
    -1.44
     parut
    -1.44
    POSITIVE LOGITS
     how
    2.11
     what
    1.79
     would
    1.77
     is
    1.76
     its
    1.73
    しますが
    1.70
    しましたが
    1.61
     bahía
    1.52
     should
    1.51
    豈
    1.47
    Activations Density 0.048%

    No Known Activations