© 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. 34-GEMMASCOPE-RES-131K
    7. 79274
    Prev
    Next
    INDEX
    Explanations

    containment and control

    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
    დი
    -0.85
    addContainerGap
    -0.80
     mewujudkan
    -0.79
     NYPD
    -0.79
     legislator
    -0.79
    μος
    -0.78
     sổ
    -0.77
     diseñador
    -0.77
     deadlock
    -0.77
    uelva
    -0.75
    POSITIVE LOGITS
     containment
    2.70
     contain
    2.61
    contain
    2.38
     containing
    2.31
    Contain
    2.19
     CONTAIN
    2.17
     Contain
    2.14
     Containment
    2.08
     Containing
    2.08
    containing
    2.08
    Activations Density 0.035%

    No Known Activations