© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15403
    Prev
    Next
    INDEX
    Explanations

    can *

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

    The neuron is firing on unusually rare or out-of-distribution tokens – i.e. words or names that barely ever occur in the text.

    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
    ि
    0.82
    ได้
    0.73
    =
    0.71
    =!
    0.70
     dover
    0.69
    Hazard
    0.66
     nostra
    0.65
    là
    0.65
    +}$
    0.64
     suo
    0.63
    POSITIVE LOGITS
     гипер
    0.85
     пыта
    0.82
    枴
    0.80
     Gres
    0.80
     transformada
    0.77
    विंद
    0.75
     diagnóstico
    0.75
    ścic
    0.75
     подобных
    0.75
     Аль
    0.74
    Activations Density 0.002%

    No Known Activations