© 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. 5631
    Prev
    Next
    INDEX
    Explanations

    only

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

    This neuron responds to long, uncommon (low‐frequency) multisyllabic 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
    有趣
    0.93
     deseas
    0.91
     comentó
    0.87
    ﺸ
    0.87
     contaba
    0.87
     kto
    0.84
     inalámb
    0.84
     usar
    0.83
     erzählt
    0.83
     trabajó
    0.82
    POSITIVE LOGITS
    t
    1.09
    ascus
    0.79
     closets
    0.78
    xious
    0.75
    court
    0.75
     closet
    0.72
     court
    0.72
    lly
    0.72
    lessly
    0.71
    ilable
    0.70
    Activations Density 0.001%

    No Known Activations