© 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. 131029
    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
     comprimidos
    -1.05
    requipa
    -1.02
     või
    -0.99
    StructEnd
    -0.98
    婪
    -0.96
     公園
    -0.96
    urez
    -0.96
     menú
    -0.95
    frastructure
    -0.95
     asma
    -0.94
    POSITIVE LOGITS
     of
    1.16
    _
    1.01
     then
    1.01
     visibly
    0.94
    了她
    0.92
     tra
    0.88
     more
    0.88
     here
    0.87
    sol
    0.86
     vs
    0.85
    Activations Density 0.000%

    No Known Activations