© 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. 56842
    Prev
    Next
    INDEX
    Explanations

    border crossing

    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
    Negative Logits
     پروفایل
    -0.94
     worldwide
    -0.93
     Oceania
    -0.90
     circon
    -0.81
     rond
    -0.79
     globale
    -0.79
     europ
    -0.78
     Europe
    -0.77
    Worldwide
    -0.76
     Africa
    -0.76
    POSITIVE LOGITS
     border
    3.14
    border
    2.58
     Border
    2.27
     across
    2.25
     crossing
    2.22
    Border
    2.16
     cross
    2.09
     bordering
    1.95
    BORDER
    1.92
     BORDER
    1.92
    Activations Density 0.069%

    No Known Activations