© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31003
    Prev
    Next
    INDEX
    Explanations

    time for activities

    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
    定了
    -1.00
     timed
    -0.96
     timing
    -0.96
     timestamp
    -0.93
     timeline
    -0.91
    此时的
    -0.90
     timeout
    -0.89
    setTimeout
    -0.85
     timescale
    -0.84
    OHN
    -0.83
    POSITIVE LOGITS
     activities
    1.02
     each
    0.99
     preparation
    0.96
    EACH
    0.96
    其他
    0.94
     pursuits
    0.93
    Ingredi
    0.93
     EACH
    0.91
    zyny
    0.91
    ――――
    0.89
    Activations Density 0.030%

    No Known Activations