© 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. 79903
    Prev
    Next
    INDEX
    Explanations

    later, tomorrow, after

    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
     sodio
    -0.80
     your
    -0.78
    出于
    -0.77
    といっても
    -0.77
     Other
    -0.75
     troppo
    -0.73
    쩍
    -0.73
    負責
    -0.73
     too
    -0.72
    ارية
    -0.71
    POSITIVE LOGITS
     later
    1.70
    Later
    1.16
    later
    1.16
    deferred
    1.09
     tomorrow
    1.07
     kés
    0.99
     afterwards
    0.96
     Later
    0.95
     earlier
    0.92
     بعد
    0.92
    Activations Density 0.059%

    No Known Activations