© 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. 29057
    Prev
    Next
    INDEX
    Explanations

    their associated properties

    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
    IVENESS
    -1.76
    های
    -1.66
    蔸
    -1.61
    閖
    -1.53
     tipi
    -1.50
     sella
    -1.49
     Romana
    -1.49
    
    -1.48
    hibits
    -1.46
     baie
    -1.46
    POSITIVE LOGITS
     Their
    1.79
     themselves
    1.74
     επίσης
    1.48
     and
    1.42
     their
    1.40
     なら
    1.40
     proporcionar
    1.38
    太多的
    1.38
     to
    1.37
     sguardo
    1.37
    Activations Density 0.119%

    No Known Activations