© 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. 63303
    Prev
    Next
    INDEX
    Explanations

    cross-border or across regions

    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
    روه
    -0.84
     промо
    -0.81
     جامعه
    -0.74
    顿
    -0.72
     BAH
    -0.71
    ♦
    -0.71
    BAH
    -0.69
    Stacey
    -0.69
     orientale
    -0.68
     noy
    -0.67
    POSITIVE LOGITS
     cross
    5.66
    cross
    4.66
    Cross
    4.25
     Cross
    4.13
    CROSS
    3.86
     CROSS
    3.73
    跨
    3.69
     crosses
    2.95
    クロス
    2.73
     crossed
    2.56
    Activations Density 0.065%

    No Known Activations