© 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. 13329
    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
     ofere
    -1.31
     appliquer
    -1.30
     personnaliser
    -1.29
     its
    -1.27
     crucial
    -1.24
     maintenir
    -1.23
    ఝ
    -1.23
     обеспечить
    -1.23
     vientos
    -1.23
    provided
    -1.21
    POSITIVE LOGITS
    ࣭
    1.50
     undeniably
    1.16
     for
    1.13
     dramatique
    1.11
     Usually
    1.10
     tireless
    1.10
     chaude
    1.09
     teatr
    1.08
    пион
    1.06
     avancée
    1.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.