© 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. 98118
    Prev
    Next
    INDEX
    Explanations

    local dialect

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

    The neuron reliably activates on text drawn from structured, key–value “infobox” entries (e.g. Wikipedia sidebar data), distinguishing those template fields from running prose.

    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
     RUE
    -0.91
    imir
    -0.81
    <?
    -0.79
     dipilih
    -0.76
    NNNN
    -0.75
    úmer
    -0.75
    Buona
    -0.75
    湄
    -0.75
     ORCH
    -0.75
    voerd
    -0.74
    POSITIVE LOGITS
     dialect
    2.56
     dialects
    2.34
     Dial
    1.95
    dialect
    1.77
    Dialect
    1.73
    Dial
    1.71
     dial
    1.61
    dial
    1.52
     диа
    1.42
     spoken
    1.34
    Activations Density 0.052%

    No Known Activations