© 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. 98644
    Prev
    Next
    INDEX
    Explanations

    time related transitions

    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
    他才
    -0.80
    いなかった
    -0.79
     canh
    -0.77
    ṃ
    -0.76
    ۆ
    -0.76
    走り
    -0.75
     loss
    -0.75
    反対
    -0.74
     ij
    -0.73
    驮
    -0.73
    POSITIVE LOGITS
     now
    2.38
     artık
    1.89
     désormais
    1.45
     henceforth
    1.45
    现在
    1.37
     since
    1.35
     теперь
    1.35
     still
    1.26
     became
    1.24
     lately
    1.24
    Activations Density 0.139%

    No Known Activations