© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15793
    Prev
    Next
    INDEX
    Explanations

    instruction delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    ټبال
    1.12
    <unused1696>
    1.10
    Ṣ
    1.06
    <unused158>
    1.03
    <unused281>
    1.03
     диагности
    1.03
    Hö
    1.02
     succinctly
    1.01
    <unused278>
    1.01
    <unused1946>
    1.00
    POSITIVE LOGITS
     time
    1.24
     other
    1.19
      
    1.19
       
    1.12
    ane
    1.03
         
    1.01
     per
    0.99
     paid
    0.98
     memory
    0.97
     good
    0.96
    Activations Density 0.094%

    No Known Activations