© 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. 104353
    Prev
    Next
    INDEX
    Explanations

    Bayern, paramedics, Ober names

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

    This neuron is a named-entity detector—it lights up on proper names and organizational or professional terms (e.g. “Bayern,” “paramedics,” “Π,” “Ober”).

    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
     be
    -3.16
     was
    -3.00
     has
    -2.97
    {
    -2.95
    al
    -2.72
     thinks
    -2.64
    d
    -2.63
     For
    -2.58
    ll
    -2.55
    讴
    -2.55
    POSITIVE LOGITS
    𐄁
    3.27
    鸸
    3.27
     ſont
    3.20
     内衣
    3.16
     frança
    3.02
    橚
    2.98
    箆
    2.97
     braço
    2.95
    揠
    2.95
    葙
    2.94
    Activations Density 0.001%

    No Known Activations