© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84749
    Prev
    Next
    INDEX
    Explanations

    Caucasian geographical names

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

    The neuron fires strongly on tokens belonging to proper nouns—especially geographic names and other specialized titles—marking the presence of multi‐token named entities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     atak
    -0.82
     Demok
    -0.73
    Advertisements
    -0.73
     Chio
    -0.73
     kore
    -0.72
    ộ
    -0.71
    Pare
    -0.71
     Odessa
    -0.71
    Amerika
    -0.71
     Amerika
    -0.71
    POSITIVE LOGITS
     Duda
    1.03
     Dag
    0.92
     aliphatic
    0.88
     Caucasian
    0.85
     Caucasus
    0.84
    numbered
    0.81
     lustig
    0.79
     !}
    0.79
     Che
    0.78
    itié
    0.77
    Activations Density 0.024%

    No Known Activations