© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112403
    Prev
    Next
    INDEX
    Explanations

    cricket scores and statistics

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

    The neuron chiefly activates on numeric tokens—digits and numeric statistics (e.g., scores, overs, and other figures).

    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
    plaatsen
    -1.43
    ënt
    -1.41
    player
    -1.41
     ("%
    -1.39
    тых
    -1.38
     одном
    -1.30
    ńska
    -1.30
    []=$
    -1.30
    ŚĆ
    -1.30
    스트
    -1.30
    POSITIVE LOGITS
    ḿ
    1.46
     kochen
    1.37
     to
    1.31
    rfan
    1.31
                    
    1.29
          
    1.23
     Asegúrese
    1.22
      
    1.20
    至於
    1.20
     知道
    1.20
    Activations Density 0.009%

    No Known Activations