© 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. 34-GEMMASCOPE-RES-131K
    7. 90812
    Prev
    Next
    INDEX
    Explanations

    past times and holidays

    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_34/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
    Earlier
    -0.82
     Earlier
    -0.80
    的确
    -0.78
    earlier
    -0.77
    當時
    -0.77
     mentes
    -0.75
     earlier
    -0.75
    τερα
    -0.75
    руп
    -0.74
     раньше
    -0.74
    POSITIVE LOGITS
     past
    1.31
     gone
    1.24
    past
    0.96
     years
    0.78
    Past
    0.74
    PAST
    0.74
     किए
    0.74
     занятий
    0.73
    ="<?=
    0.73
     passato
    0.73
    Activations Density 0.026%

    No Known Activations