© 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. 10-GEMMASCOPE-RES-131K
    7. 19290
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

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

    This neuron activates on individual named-entity tokens—single words that serve as proper names (e.g. place names, personal names, organization names, 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_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
    
    -2.92
     They
    -2.86
     juzg
    -2.78
     човек
    -2.72
     пър
    -2.67
     famosas
    -2.64
    哢
    -2.59
    ୌ
    -2.58
    ᨕ
    -2.56
    
    -2.50
    POSITIVE LOGITS
    K
    3.70
    '
    3.31
    on
    3.28
    {
    3.17
    G
    3.03
     they
    2.95
     остальные
    2.84
    as
    2.78
    na
    2.77
    is
    2.61
    Activations Density 0.051%

    No Known Activations