© 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. 74952
    Prev
    Next
    INDEX
    Explanations

    claims priority to patent applications

    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
     them
    -1.32
     they
    -1.24
     their
    -1.18
     kutoka
    -1.01
     geladeira
    -1.00
     xícara
    -0.98
     rubia
    -0.94
     ofici
    -0.93
     rique
    -0.93
     suficiente
    -0.91
    POSITIVE LOGITS
     также
    1.23
     earlier
    1.13
     Evangelio
    1.09
     which
    1.09
    ggars
    1.08
     również
    1.04
     myös
    1.03
    鴦
    1.02
    єра
    1.02
    ַּ
    0.98
    Activations Density 0.049%

    No Known Activations