© 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. 24-GEMMASCOPE-2-RES-16K
    4. 6147
    Prev
    Next
    INDEX
    Explanations

    separators and code delimiters

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

    The neuron fires on isolated identifier‐style tokens—things like legal section abbreviations (e.g. “IN”), bits of domain names (“yin”), standalone digits (“3”), or prefix fragments (“co-”)—i.e. short alphanumeric/abbreviation tokens used as technical or legal identifiers.

    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
       
    0.54
    	
    0.54
         
    0.50
     thousands
    0.49
     five
    0.46
        
    0.45
     nine
    0.45
     hundreds
    0.45
    		
    0.43
    n
    0.43
    POSITIVE LOGITS
     வேற
    0.61
     ተመሳሳይ
    0.61
     ähn
    0.58
     żad
    0.58
     కూడా
    0.55
     тоже
    0.55
     separar
    0.52
     mód
    0.52
     scheint
    0.52
     অন্য
    0.51
    Activations Density 0.000%

    No Known Activations