© 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. 74874
    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
    嗲
    -1.11
    RAINE
    -1.10
     Phòng
    -1.08
    opedia
    -1.08
     Cocina
    -1.06
    円
    -1.06
    了一個
    -1.05
     partenaire
    -1.05
    (\%)
    -1.03
    켠
    -1.03
    POSITIVE LOGITS
    Compared
    1.47
    Contrary
    1.43
    Depending
    1.38
    Leírás
    1.38
    Generally
    1.37
    Adding
    1.32
    Almost
    1.30
    Because
    1.28
    Surprisingly
    1.28
    Getting
    1.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.