© 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. 13046
    Prev
    Next
    INDEX
    Explanations

    comprehensive analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    emissions
    -1.30
     danos
    -1.27
     kamer
    -1.25
     belg
    -1.24
     sitten
    -1.24
     современного
    -1.22
    xvi
    -1.19
     silikon
    -1.19
     adalah
    -1.17
     alko
    -1.17
    POSITIVE LOGITS
     should
    1.27
     with
    1.18
     spurred
    1.11
     decided
    1.01
     out
    1.00
     on
    0.98
     provides
    0.96
     began
    0.96
     after
    0.94
     does
    0.94
    Activations Density 0.020%

    No Known Activations