© 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. 9745
    Prev
    Next
    INDEX
    Explanations

    nod offer anthem time comment

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

    This neuron fires strongly on uncommon, content-bearing words (rare nouns, verbs, and adjectives) rather than on common function 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
    ClickListener
    0.86
    籟
    0.75
    delen
    0.74
    вший
    0.72
     తిరిగి
    0.70
    শির
    0.70
    eredith
    0.68
    蹿
    0.68
    utiérrez
    0.68
    ందని
    0.67
    POSITIVE LOGITS
    t
    0.98
    تج
    0.87
    .
    0.79
    ت
    0.79
    ı
    0.78
    g
    0.77
    ポケモン
    0.75
     التجارية
    0.72
    bright
    0.72
     ต้อง
    0.71
    Activations Density 0.000%

    No Known Activations