© 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. 10372
    Prev
    Next
    INDEX
    Explanations

    Introduction after "The"

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

    The neuron fires strongly on mentions of puppies (and related puppy/dog contexts).

    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
     కూడా
    0.79
     सुद्धा
    0.76
     expts
    0.74
     ਵੀ
    0.73
     المشروع
    0.70
     גם
    0.70
    も含
    0.70
    訸
    0.69
    ススメ
    0.67
     таксама
    0.67
    POSITIVE LOGITS
     countless
    0.88
    ─
    0.86
     famously
    0.84
    ­
    0.82
     undeniably
    0.82
     কিংবা
    0.81
     myriad
    0.79
     ketika
    0.78
    ––
    0.78
     arguably
    0.76
    Activations Density 1.123%

    No Known Activations