© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65508
    Prev
    Next
    INDEX
    Explanations

    Moroccan North African locations

    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
    ⴻ
    -1.13
     informaci
    -0.90
    sampler
    -0.87
    Beijo
    -0.85
     возмо
    -0.85
    Beijos
    -0.81
    HOW
    -0.81
    rox
    -0.79
     differences
    -0.78
     exklu
    -0.78
    POSITIVE LOGITS
     Morocco
    1.18
     Moroccan
    1.15
     Algeria
    1.09
    Algeria
    1.08
     Rabat
    1.06
     Carthage
    1.04
     Casablanca
    1.03
     Magh
    1.03
     Amaz
    1.00
     Algerian
    1.00
    Activations Density 0.020%

    No Known Activations