© 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. 193
    Prev
    Next
    INDEX
    Explanations

    and followed by a connecting word

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

    The neuron strongly activates on the conjunction “and” (including sentence-initial “And”).

    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
    0.55
            
    0.40
    1
    0.40
        
    0.39
         
    0.38
                          
    0.37
    <0x0D>
    0.37
    0.37
    0
    0.37
          
    0.36
    POSITIVE LOGITS
     sebagainya
    0.48
     whatnot
    0.43
     ఇతర
    0.43
    အတူ
    0.39
     především
    0.39
    ppure
    0.39
     كذلك
    0.39
     insbesondere
    0.38
     sobretudo
    0.38
     współpracy
    0.38
    Activations Density 0.890%

    No Known Activations