© 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. 15723
    Prev
    Next
    INDEX
    Explanations

    p/q and ≠ 0

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

    The neuron fires on rare or low-frequency tokens—i.e. unusually obscure or uncommon words.

    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
    ہار
    0.79
    پے
    0.78
    ată
    0.77
    Opin
    0.77
     Pyaar
    0.76
    ází
    0.74
    ārt
    0.74
    ৫
    0.74
    ادہ
    0.73
     Opinions
    0.72
    POSITIVE LOGITS
     kepad
    0.81
     magnum
    0.78
    JlcG
    0.75
     кожу
    0.74
     пони
    0.71
     кроме
    0.70
    dus
    0.70
     suda
    0.69
    
    0.68
     unut
    0.67
    Activations Density 0.002%

    No Known Activations