© 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. 22-GEMMASCOPE-RES-131K
    7. 67627
    Prev
    Next
    INDEX
    Explanations

    United States history and events

    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_22/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
     this
    -1.22
     young
    -1.12
     family
    -1.03
    itteet
    -0.99
    你去
    -0.98
    也非常
    -0.98
    了很多
    -0.97
     families
    -0.96
     şehir
    -0.96
    ريقة
    -0.96
    POSITIVE LOGITS
     så
    1.22
    albeit
    1.21
     suya
    1.10
     "../../../../
    1.09
     المصرية
    1.09
    whose
    1.05
    ych
    1.05
    Thus
    1.05
     its
    1.04
    その
    1.04
    Activations Density 0.218%

    No Known Activations