© 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. 60744
    Prev
    Next
    INDEX
    Explanations

    telling time / time keeping

    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
     clocks
    -1.13
     CLOCK
    -1.00
     clock
    -1.00
    CLOCK
    -0.99
    clock
    -0.94
    Clock
    -0.92
     Clock
    -0.91
     dial
    -0.91
     hourglass
    -0.88
     Thornton
    -0.84
    POSITIVE LOGITS
     telling
    1.56
     tell
    1.39
     tells
    1.20
    telling
    1.19
    Telling
    1.16
     Telling
    1.11
     keeping
    1.07
    keeping
    1.05
     time
    0.98
     Keeping
    0.98
    Activations Density 0.034%

    No Known Activations