© 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. 71540
    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
     get
    -1.36
     before
    -1.17
     really
    -1.16
     set
    -1.16
     full
    -1.16
    PyTuple
    -1.12
     start
    -1.12
     more
    -1.09
     actually
    -1.07
     started
    -1.05
    POSITIVE LOGITS
    MTS
    1.13
     idiotic
    1.11
    了一句
    1.11
     firs
    1.09
    连忙
    1.09
     terrific
    1.08
     mung
    1.08
     chao
    1.07
     astounding
    1.06
     espesor
    1.05
    Activations Density 0.000%

    No Known Activations