© 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. 75015
    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
     swojego
    -1.19
    iation
    -1.15
     animals
    -1.14
    utre
    -1.08
     water
    -1.06
     azúcar
    -1.04
     cabello
    -1.04
     करे
    -1.03
    itic
    -1.03
     they
    -1.03
    POSITIVE LOGITS
     jaunes
    1.07
    Fernsehserie
    1.06
    écrivain
    1.02
    勫
    1.00
     inapropiados
    0.99
    ごちそうさまでした
    0.99
     влияет
    0.98
    はかなり
    0.97
     söyl
    0.96
    Asie
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.