© 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. 34686
    Prev
    Next
    INDEX
    Explanations

    cricket bowling and fielding

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    パード
    -0.82
     Sudoku
    -0.77
     IEnumerable
    -0.73
     مقاوم
    -0.71
    вана
    -0.70
    accessToken
    -0.70
    Shaft
    -0.69
    ших
    -0.69
    неш
    -0.68
    
    -0.68
    POSITIVE LOGITS
     fielder
    0.91
     dives
    0.85
     field
    0.85
     deep
    0.82
    Region
    0.81
     slip
    0.80
     substitutes
    0.79
     region
    0.79
     positions
    0.77
     Region
    0.77
    Activations Density 0.014%

    No Known Activations