© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10890
    Prev
    Next
    INDEX
    Explanations

    c code generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    Requires
    0.65
    friction
    0.64
    ợp
    0.62
    gitignore
    0.61
    etna
    0.61
    sufficient
    0.60
    ❤️❤️
    0.58
    onz
    0.58
    érez
    0.57
    harris
    0.57
    POSITIVE LOGITS
        
    0.66
            
    0.66
             
    0.61
     Sala
    0.59
       
    0.59
     Jul
    0.57
         
    0.56
          
    0.55
     maa
    0.54
      
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.