© 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. 89844
    Prev
    Next
    INDEX
    Explanations

    local/native origin descriptors

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

    The neuron detects references to local or domestic/regional content (e.g. words like “local,” “domestic,” and “indigenous”).

    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
     Quân
    -0.85
    Writers
    -0.81
     رائعة
    -0.80
     rése
    -0.78
     éta
    -0.78
     différents
    -0.77
    說話
    -0.77
    DUN
    -0.76
     реклам
    -0.74
     correto
    -0.74
    POSITIVE LOGITS
     counterpart
    1.06
     consumption
    1.04
     indigenous
    1.00
    érez
    0.95
     produced
    0.95
     produces
    0.94
     counterparts
    0.94
     content
    0.93
     talent
    0.92
    消化
    0.92
    Activations Density 0.023%

    No Known Activations