© 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. 98560
    Prev
    Next
    INDEX
    Explanations

    '../' or '@' after "from"

    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
     akar
    -1.16
    および
    -1.14
    гали
    -1.06
     verrez
    -1.04
    strahlung
    -1.03
     famille
    -1.03
    ܪ
    -0.98
     églises
    -0.96
    ぐり
    -0.94
    وگرافی
    -0.94
    POSITIVE LOGITS
    athered
    1.02
     ovviamente
    1.00
    当我
    0.98
     evidentemente
    0.97
     zugesch
    0.95
    wrote
    0.91
    ätie
    0.91
    なんですね
    0.90
    Onder
    0.90
    ărilor
    0.89
    Activations Density 0.004%

    No Known Activations