© 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. 10-GEMMASCOPE-RES-131K
    4. 61373
    Prev
    Next
    INDEX
    Explanations

    Montenegro and Balkan countries

    np_acts-logits-general · gemini-2.5-flash-lite

    The main thing this neuron does is detect mentions of “Montenegro” (and its adjectival/demonym forms like “Montenegrin”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     terutama
    -1.66
    鶿
    -1.60
    籏
    -1.60
     Discovering
    -1.59
     belirt
    -1.54
     proveniente
    -1.50
    I
    -1.49
     Designing
    -1.48
     Therefore
    -1.48
    鴬
    -1.48
    POSITIVE LOGITS
    }$,
    1.80
    )$.
    1.67
    ."
    1.66
    趼
    1.65
    祧
    1.63
    )$,
    1.60
    \}$.
    1.59
    蠃
    1.59
    ྃ
    1.59
    ()]);
    1.59
    Activations Density 0.011%

    No Known Activations