© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26872
    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
     volledige
    -1.20
     monstruo
    -1.15
     auténtico
    -1.15
    蛱
    -1.11
     émotions
    -1.05
     vijf
    -1.05
     groei
    -1.04
     zapato
    -1.03
     évé
    -1.01
     héroe
    -1.00
    POSITIVE LOGITS
    ਾਰ
    1.05
     which
    0.96
     out
    0.95
    pageX
    0.93
    Răsp
    0.93
     شده
    0.91
    RTLI
    0.90
    に行きました
    0.90
     veloc
    0.88
     которая
    0.87
    Activations Density 0.004%

    No Known Activations