© 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. 74970
    Prev
    Next
    INDEX
    Explanations

    actions before or after events

    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
    ようです
    -1.03
     ormai
    -1.00
    F
    -0.96
     désormais
    -0.95
     henceforth
    -0.94
     Зачем
    -0.93
     besucht
    -0.93
     возникает
    -0.92
     my
    -0.91
     alimenti
    -0.91
    POSITIVE LOGITS
     before
    2.97
     during
    2.89
     after
    2.80
     when
    2.61
     після
    1.81
     prior
    1.78
     while
    1.67
     أثناء
    1.59
     early
    1.59
     после
    1.57
    Activations Density 0.274%

    No Known Activations