© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14221
    Prev
    Next
    INDEX
    Explanations

    sense

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on standout tokens—proper names, numbers, or other capitalized words—that tend to serve as headings or key labels in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    ून
    0.79
    商品の
    0.77
     फूलों
    0.74
    旛
    0.71
    ябрь
    0.71
     વિચાર
    0.71
     patching
    0.70
    ಿದ್ದೇನೆ
    0.70
     handsets
    0.70
     बैठने
    0.68
    POSITIVE LOGITS
     dette
    0.95
            
    0.95
                
    0.93
        
    0.90
           
    0.89
          
    0.89
         
    0.86
    I
    0.84
             
    0.83
     kass
    0.81
    Activations Density 0.001%

    No Known Activations