© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6969
    Prev
    Next
    INDEX
    Explanations

    Tampa Bay

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

    The neuron is keyed to pick out sports recap metadata—team and venue names, dates, and score or matchup terms.

    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
     implies
    -0.79
     personajes
    -0.75
    pico
    -0.72
     Duet
    -0.70
     demuestra
    -0.70
     iArr
    -0.69
     進
    -0.67
    ELESS
    -0.66
    Nog
    -0.66
     perfusion
    -0.66
    POSITIVE LOGITS
    Tampa
    1.21
     Tampa
    1.16
     Kerala
    0.97
     Bucs
    0.94
     спра
    0.91
     Sarasota
    0.88
    ᶦ
    0.85
     Buccaneers
    0.81
     Clearwater
    0.79
    Kerala
    0.78
    Activations Density 0.023%

    No Known Activations