© 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. 69021
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     бампер
    -1.62
     our
    -1.48
     Nedir
    -1.36
     Bakter
    -1.34
     unseren
    -1.31
     нашей
    -1.31
    ほんとに
    -1.28
     हमारे
    -1.27
     también
    -1.26
     начин
    -1.25
    POSITIVE LOGITS
    Neden
    1.64
    eseorang
    1.43
    ὴν
    1.42
     cukru
    1.41
    Karakter
    1.41
    硕士
    1.41
    Ekster
    1.38
    第五
    1.38
     hierbas
    1.33
     daring
    1.30
    Activations Density 0.000%

    No Known Activations