© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8451
    Prev
    Next
    INDEX
    Explanations

    cricket players and events

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

    cricket

    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_31_width_262k_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
    Celeron
    0.57
    豬
    0.55
     مە
    0.54
     Sist
    0.54
     Hanna
    0.53
     Eber
    0.52
     قلم
    0.52
     κε
    0.52
     travertine
    0.52
     Carolyn
    0.51
    POSITIVE LOGITS
     cricket
    1.30
     cricketer
    1.28
     batsmen
    1.27
     cricketers
    1.27
     क्रिकेट
    1.21
     batsman
    1.18
    🏏
    1.18
     క్రికె
    1.13
     crick
    1.10
     ক্রিকে
    1.10
    Activations Density 0.049%

    No Known Activations