© 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. 72941
    Prev
    Next
    INDEX
    Explanations

    is called

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

    The neuron activates on multi‐word technical term introductions—phrases where something is “called,” “known as,” or “dubbed” (i.e. naming or defining a concept).

    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
    そんな
    -1.30
    不同
    -1.27
    そう
    -1.19
     {
    
    -1.18
    那么
    -1.17
     deth
    -1.17
     один
    -1.17
    Выводы
    -1.17
    となると
    -1.16
     kidna
    -1.15
    POSITIVE LOGITS
     because
    1.53
    蟊
    1.51
     they
    1.51
    cable
    1.46
     for
    1.46
     but
    1.45
    €”
    1.35
    有任何
    1.34
     we
    1.32
     today
    1.32
    Activations Density 0.093%

    No Known Activations