© 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. 98685
    Prev
    Next
    INDEX
    Explanations

    schedule and timers

    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
     Platz
    -0.81
    PARATION
    -0.80
     Վեր
    -0.78
     тільки
    -0.74
     transported
    -0.74
     Kassen
    -0.74
     orgánica
    -0.73
     Ruhe
    -0.73
    only
    -0.72
    Maks
    -0.71
    POSITIVE LOGITS
     scheduled
    1.19
    scheduled
    1.15
     Scheduled
    1.13
    Cancel
    1.07
    Scheduled
    1.05
     recurring
    1.01
    cheduled
    1.00
    schedule
    0.96
     cancels
    0.96
     Cancel
    0.93
    Activations Density 0.026%

    No Known Activations