© 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. 108
    Prev
    Next
    INDEX
    Explanations

    like/love/enjoy

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

    The neuron flags enthusiastic first-person expressions of positive sentiment—especially “love,” “enjoy,” and similar declarations of affection or enjoyment.

    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_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
    	
    0.35
    					
    0.34
    <0x0D>
    0.32
    Ⲕ
    0.31
    },{"
    0.31
    ">
    0.31
     
    0.30
    				
    0.30
    						
    0.29
    			
    0.29
    POSITIVE LOGITS
     seeing
    0.70
     chatting
    0.69
     experimenting
    0.69
     watching
    0.66
     hearing
    0.61
     cuddling
    0.61
     photographing
    0.60
     tinkering
    0.60
     getting
    0.59
     tweaking
    0.57
    Activations Density 0.566%

    No Known Activations