© 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. 92602
    Prev
    Next
    INDEX
    Explanations

    China related entities

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

    The neuron specializes in spotting institutional or organizational names (e.g. affiliations and proper‐noun labels of centers, associations, databases, etc.).

    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
     koncentr
    -0.85
    Ҝ
    -0.81
    lxt
    -0.78
    かれています
    -0.77
    gabri
    -0.75
    𝖠
    -0.75
    episodes
    -0.75
    ufige
    -0.73
     koncer
    -0.73
    cxt
    -0.73
    POSITIVE LOGITS
     табле
    0.77
    лей
    0.76
    ུང་
    0.75
    nies
    0.73
     Mush
    0.71
     ample
    0.69
    uminazione
    0.69
    这
    0.69
    othelioma
    0.69
    dz
    0.69
    Activations Density 0.018%

    No Known Activations