© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63099
    Prev
    Next
    INDEX
    Explanations

    ATP tennis matches

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

    The neuron is primarily detecting numeric tokens—especially multi‐digit numbers and en‐dash–separated score or date ranges (e.g. match scores and years).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    glLoad
    -0.80
    świ
    -0.80
     Reisen
    -0.74
    beforeAll
    -0.72
    AxisSize
    -0.72
     hagas
    -0.71
    tasche
    -0.70
     Archiproducts
    -0.70
     nào
    -0.69
    agles
    -0.69
    POSITIVE LOGITS
    diki
    0.82
     fit
    0.82
     footsteps
    0.81
     ATP
    0.77
     Verhältnisse
    0.73
    Fit
    0.73
    AppSettings
    0.71
    ény
    0.71
    眾
    0.71
    ++)
    0.70
    Activations Density 0.048%

    No Known Activations