© 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. 164
    Prev
    Next
    INDEX
    Explanations

    Pronunciations and foreign words

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

    The neuron fires on tokens that name discussion spaces or documentation (e.g. “thread,” “forum,” “docs”), i.e. it detects references to online discussion or help pages.

    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
    whose
    0.42
    Таким
    0.40
     thereby
    0.38
    とともに
    0.38
    Accom
    0.38
    Chúng
    0.37
    				
    0.37
    accompanied
    0.37
    
    0.37
                  
    0.37
    POSITIVE LOGITS
     alot
    0.64
     crappy
    0.64
     guys
    0.62
     idk
    0.60
    してる
    0.57
     kinda
    0.57
     guy
    0.54
     tengo
    0.54
     veldig
    0.54
     weird
    0.54
    Activations Density 0.000%

    No Known Activations