© 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. 22-GEMMASCOPE-RES-131K
    4. 66425
    Prev
    Next
    INDEX
    Explanations

    geographical areas and 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_22/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
     natuurlijke
    -1.27
     ちゃ
    -1.23
     gevonden
    -1.23
    americanas
    -1.18
     vermute
    -1.16
     vettore
    -1.16
     estadísticas
    -1.16
     altijd
    -1.15
    kaos
    -1.14
    pedidos
    -1.14
    POSITIVE LOGITS
     area
    1.35
    LOCAL
    1.34
    region
    1.24
     of
    1.23
        
    1.23
     region
    1.22
     क्षेत्र
    1.20
     Area
    1.19
    d
    1.16
       
    1.12
    Activations Density 0.036%

    No Known Activations