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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 6142
    Prev
    Next
    INDEX
    Explanations

    cricket and its formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     monof
    0.51
    جون
    0.50
    豬
    0.49
     صہیونیوں
    0.49
    Celeron
    0.48
     Maret
    0.48
     eut
    0.47
     Alexandria
    0.46
     Antio
    0.46
     പ്രവർത്തന
    0.46
    POSITIVE LOGITS
     cricket
    1.88
     cricketer
    1.65
     cricketers
    1.65
    🏏
    1.63
     crick
    1.62
     Cricket
    1.61
    Cricket
    1.61
     batsman
    1.59
     batsmen
    1.59
     क्रिकेट
    1.56
    Activations Density 0.013%

    No Known Activations