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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118781
    Prev
    Next
    INDEX
    Explanations

    places in Poland

    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
     Krakowie
    -0.79
     Katze
    -0.79
     Hütte
    -0.75
     heuer
    -0.74
     warszaw
    -0.74
     Polskiej
    -0.73
     mewakili
    -0.71
    冲
    -0.69
    ئية
    -0.68
     Sándor
    -0.68
    POSITIVE LOGITS
     Poland
    1.18
    Poland
    1.07
     Поль
    1.06
     Polish
    1.03
     Siles
    0.94
     Pomer
    0.86
     lesz
    0.85
     поль
    0.85
     Brandenburg
    0.84
     Chopin
    0.83
    Activations Density 0.038%

    No Known Activations