© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 61075
    Prev
    Next
    INDEX
    Explanations

    Yaz, ESL, Oldham

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

    The neuron fires on tokens that are part of capitalized named entities or acronyms (e.g. place names, person names, organization abbreviations).

    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
     But
    -2.97
     alrededores
    -2.59
     he
    -2.52
    
    -2.52
     แต่
    -2.44
    
    -2.41
     sogenannten
    -2.36
     klassischen
    -2.36
    enablog
    -2.27
     ähnlichen
    -2.22
    POSITIVE LOGITS
    N
    2.72
    A
    2.67
    俢
    2.64
    {
    2.56
    鼙
    2.53
    ଞ
    2.42
    ၞ
    2.36
    骘
    2.33
    蓴
    2.28
    most
    2.23
    Activations Density 0.002%

    No Known Activations