© 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. 12753
    Prev
    Next
    INDEX
    Explanations

    sports teams and awards

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

    The neuron is triggered by proper-noun sequences naming organizations, teams, awards, or other formal entities.

    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
     Ucraina
    -1.23
    客様
    -1.14
    上的
    -1.12
    ują
    -1.11
    akit
    -1.07
    chrift
    -1.05
    Relevant
    -1.05
    不同
    -1.05
    finch
    -1.05
    Adapter
    -1.04
    POSITIVE LOGITS
     them
    1.99
     those
    1.47
     such
    1.37
     who
    1.34
     again
    1.31
     there
    1.27
    fanart
    1.25
    引き続き
    1.23
     Flies
    1.22
     rozší
    1.20
    Activations Density 0.050%

    No Known Activations