Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7747
    Prev
    Next
    INDEX
    Explanations

    thank you / thanks

    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
     ۱
    -0.87
    当局
    -0.86
     Brasileira
    -0.81
    smt
    -0.80
     mondo
    -0.78
    嫌疑
    -0.77
    dekat
    -0.76
     Alemanha
    -0.76
    Enfin
    -0.76
    プション
    -0.76
    POSITIVE LOGITS
     THANK
    1.24
     Thank
    1.23
     thank
    1.17
     ppt
    1.15
     powerpoint
    1.10
    thank
    1.08
    Thank
    1.05
     hablando
    1.03
     thanking
    0.99
     thankful
    0.98
    Activations Density 0.002%

    No Known Activations