© 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. 35914
    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
     balkon
    -1.30
     setembro
    -1.13
     يمكنك
    -1.09
     münchen
    -1.08
     Gebruik
    -1.05
     Nedir
    -1.05
     komis
    -1.05
     Kalifor
    -1.04
     zapatillas
    -1.02
     balón
    -1.02
    POSITIVE LOGITS
    两种
    1.24
     is
    1.20
     has
    1.18
     in
    1.05
     the
    1.03
     two
    0.98
     even
    0.98
     various
    0.98
     have
    0.97
     especially
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.