© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130489
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to tokens characteristic of sports reporting—especially numbers, scores, team names, and game‐statistic terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    team winning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    節目
    -1.02
    rira
    -0.96
    購物
    -0.94
    Many
    -0.93
    nisk
    -0.90
     Tän
    -0.89
    employment
    -0.89
    Penulis
    -0.88
     or
    -0.88
    갖
    -0.88
    POSITIVE LOGITS
     продви
    1.02
     інших
    1.01
     elfog
    0.96
    运转
    0.94
    FORMAN
    0.94
    myapplication
    0.92
     dedos
    0.92
    respec
    0.91
     layui
    0.91
     esta
    0.90
    Activations Density 0.026%

    No Known Activations