© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2930
    Prev
    Next
    INDEX
    Explanations

    Laptop/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
    7
    0.87
    七
    0.81
    ៧
    0.80
    ٧
    0.79
     बृहस्पतिवार
    0.78
    ७
    0.78
    ༧
    0.78
     Zee
    0.74
    ░
    0.73
     ৭৭
    0.73
    POSITIVE LOGITS
                
    1.85
                 
    1.39
               
    1.27
                  
    1.25
    ---------
    1.15
     ---------
    0.98
    ...........
    0.93
    0.92
    ---------*/
    0.92
     =========
    0.90
    Activations Density 0.101%

    No Known Activations