© 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. 34745
    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
    品です
    -1.16
     its
    -1.04
     tắt
    -0.98
     their
    -0.96
     within
    -0.94
     suara
    -0.91
    انيف
    -0.91
    oodoo
    -0.88
     small
    -0.88
     before
    -0.86
    POSITIVE LOGITS
     ChatGPT
    1.01
     Celine
    0.94
     chao
    0.90
    lap
    0.89
     éviter
    0.88
    Musk
    0.88
     NFTs
    0.87
    fting
    0.85
     چنین
    0.84
    ggen
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.