© 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. 105218
    Prev
    Next
    INDEX
    Explanations

    sports scores and results

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

    The neuron fires on golf competition details—references to tournament names, rounds, scores, and related numeric results.

    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
    alism
    -1.58
    </b>
    -1.48
    k
    -1.41
    StoryboardSegue
    -1.41
    当你
    -1.40
     who
    -1.38
    当我
    -1.34
    if
    -1.32
    aw
    -1.29
    Why
    -1.29
    POSITIVE LOGITS
     vermutlich
    1.49
     möglicherweise
    1.41
     Latinoamérica
    1.29
     として
    1.27
    
    1.24
    TINGS
    1.23
     zwycię
    1.23
     afgelopen
    1.23
    nữ
    1.23
    ῖ
    1.20
    Activations Density 0.009%

    No Known Activations