© 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. 34-GEMMASCOPE-RES-131K
    7. 91823
    Prev
    Next
    INDEX
    Explanations

    basketball rebounds

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

    The neuron flags numeric statistics—especially counts of points, rebounds, assists, and similar game‐report figures.

    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
    retirement
    -0.88
     planas
    -0.76
    rainy
    -0.76
     Retirement
    -0.75
    remains
    -0.75
     bizi
    -0.74
     Greece
    -0.74
     taxed
    -0.72
     experimento
    -0.71
     प
    -0.71
    POSITIVE LOGITS
     rebound
    4.09
     rebounds
    3.45
     boards
    1.73
     reb
    1.52
     board
    1.44
    boards
    1.44
    Re
    1.40
    Board
    1.34
     Reb
    1.32
     Bounce
    1.30
    Activations Density 0.015%

    No Known Activations