© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25283
    Prev
    Next
    INDEX
    Explanations

    duration of events

    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
     shelving
    -0.85
     syncing
    -0.83
    ந்த
    -0.83
     doar
    -0.82
    Quar
    -0.82
     victoires
    -0.81
     toate
    -0.80
     đổi
    -0.79
     mantenimiento
    -0.78
     idag
    -0.78
    POSITIVE LOGITS
     duration
    1.05
     preparation
    0.96
    ViewInit
    0.96
    ImageContext
    0.95
     lasts
    0.93
     participant
    0.88
     project
    0.88
     participants
    0.88
    aconda
    0.87
     final
    0.86
    Activations Density 0.120%

    No Known Activations