© 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. 83457
    Prev
    Next
    INDEX
    Explanations

    start of phrase or question

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

    This neuron detects references to sports match reports, specifically team names and associated game statistics.

    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
    Which
    -0.94
    Because
    -0.93
    Additionally
    -0.87
    Although
    -0.86
     Because
    -0.85
    iterable
    -0.84
    Also
    -0.83
    Ayrıca
    -0.82
     continual
    -0.78
    ₍
    -0.78
    POSITIVE LOGITS
    焊
    0.88
    ;”
    0.86
    skinned
    0.84
    钼
    0.79
    と言われて
    0.79
     fant
    0.78
    while
    0.77
    レール
    0.77
    łam
    0.77
     salvare
    0.77
    Activations Density 0.000%

    No Known Activations