© 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. 10-GEMMASCOPE-RES-131K
    7. 42616
    Prev
    Next
    INDEX
    Explanations

    sports league matchups

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

    The neuron fires strongly on tokens appearing in sports–oriented match previews and event write-ups, i.e. prose describing upcoming games, fixtures, or sporting contests.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     when
    -2.19
     diverso
    -1.44
     during
    -1.42
     using
    -1.39
     когда
    -1.38
    Anzeige
    -1.35
    Begriff
    -1.34
     When
    -1.34
     diversas
    -1.33
    ными
    -1.32
    POSITIVE LOGITS
    🪙
    1.53
    inheritDoc
    1.48
    最近の
    1.40
     NUCLEAR
    1.38
    の準備
    1.36
    🪛
    1.36
     upcoming
    1.35
     lately
    1.35
    September
    1.34
    ṝ
    1.34
    Activations Density 0.048%

    No Known Activations