© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111482
    Prev
    Next
    INDEX
    Explanations

    Morocco and Moroccan

    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_10/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
    樒
    -2.95
    杁
    -2.84
    y
    -2.66
     sooo
    -2.55
    ⸂
    -2.42
     magnificent
    -2.39
     soooo
    -2.38
    颪
    -2.33
    鸲
    -2.33
    乆
    -2.25
    POSITIVE LOGITS
    </td>
    2.47
     Morocco
    2.36
     и
    2.20
    Y
    2.16
    enegger
    2.05
     supremely
    2.02
    龊
    1.99
    あた
    1.97
     और
    1.96
     That
    1.95
    Activations Density 0.002%

    No Known Activations