© 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. 28386
    Prev
    Next
    INDEX
    Explanations

    before introducing a topic

    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
     when
    -1.60
     когда
    -1.23
     whereas
    -1.09
     když
    -1.05
    yaç
    -1.02
    cex
    -1.02
     cuando
    -1.01
     también
    -0.99
     quando
    -0.97
    ês
    -0.93
    POSITIVE LOGITS
     we
    1.40
     unaweza
    1.14
    我們
    1.04
     actual
    0.96
    We
    0.94
    がこの
    0.91
     internationaux
    0.91
    我们
    0.89
     мы
    0.89
    进一步
    0.88
    Activations Density 0.017%

    No Known Activations