© 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. 40211
    Prev
    Next
    INDEX
    Explanations

    consequence/conclusion words

    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
     måske
    -1.01
    口中
    -0.90
     questa
    -0.84
     aim
    -0.84
     noget
    -0.83
    ksiä
    -0.82
     seus
    -0.81
     своей
    -0.79
    alloon
    -0.79
    monės
    -0.78
    POSITIVE LOGITS
     Therefore
    1.70
     therefore
    1.66
     поэтому
    1.44
    Therefore
    1.34
     Поэтому
    1.28
     therefor
    1.25
     więc
    1.19
    而不是
    1.17
     quindi
    1.17
    所以
    1.17
    Activations Density 0.099%

    No Known Activations