© 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. 929
    Prev
    Next
    INDEX
    Explanations

    for each item

    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
     of
    -1.77
     Because
    -1.76
     When
    -1.57
    Other
    -1.55
     Several
    -1.52
     untuk
    -1.48
    Surprisingly
    -1.48
     by
    -1.48
     السياس
    -1.46
    unjungi
    -1.46
    POSITIVE LOGITS
    ܆
    1.66
    ↵↵↵
    1.63
     distintos
    1.60
     onze
    1.60
     Inſ
    1.59
    
    1.58
     possono
    1.58
     vitales
    1.57
     vengono
    1.56
    鼱
    1.55
    Activations Density 0.038%

    No Known Activations