© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5880
    Prev
    Next
    INDEX
    Explanations

    cricket and its related terms

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

    cricket and related cricket terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಿದ್ದಾನೆ
    0.49
     ל
    0.47
    行業
    0.47
     ವ್ಯವ
    0.46
     പ്രവർത്തന
    0.45
     പ്രവര്‍ത്തന
    0.44
    ㄟ
    0.43
    μμ
    0.43
     सुचेता
    0.42
     Eurasian
    0.42
    POSITIVE LOGITS
     cricket
    2.17
     cricketers
    2.09
     batsman
    2.05
     cricketer
    2.03
    Cricket
    2.03
     Cricket
    2.02
     batsmen
    2.02
     wicket
    1.92
     crick
    1.92
     batting
    1.91
    Activations Density 0.115%

    No Known Activations