© 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. 22-GEMMASCOPE-RES-131K
    7. 71728
    Prev
    Next
    INDEX
    Explanations

    tennis match scores and names

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

    The neuron fires on numeric score tokens in sports match 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_22/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
     who
    -1.26
     will
    -1.21
     also
    -1.13
     some
    -1.08
     for
    -1.08
     know
    -1.01
     looks
    -0.99
     都
    -0.99
     all
    -0.96
     those
    -0.94
    POSITIVE LOGITS
     magasiner
    1.07
    躄
    1.05
    approx
    1.05
     tjän
    1.03
    љено
    1.02
    håll
    1.02
     مشاه
    1.00
    额头
    1.00
    jorde
    0.99
     Ван
    0.99
    Activations Density 0.000%

    No Known Activations