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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1611
    Prev
    Next
    INDEX
    Explanations

    knowledge based on training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    Trav
    1.01
     children
    1.01
    ชีวิต
    1.00
     xa
    0.96
    Ho
    0.93
    了
    0.92
    ตา
    0.92
    王的
    0.91
     считается
    0.90
     Rai
    0.90
    POSITIVE LOGITS
    ফাই
    1.50
    
    1.46
    بيوتر
    1.46
    ilizar
    1.43
     filePath
    1.42
    paired
    1.41
    ফিক
    1.41
    focused
    1.41
    ாக
    1.40
    प्लो
    1.39
    Activations Density 0.386%

    No Known Activations