© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 834
    Prev
    Next
    INDEX
    Explanations

    contextual domains

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

    The neuron selectively lights up on prominent content nouns—the head words of noun phrases (e.g. “portfolio,” “offerings,” “game,” “program,” “family,” “line,” “pack,” etc.) that typically name products, collections, or other key entities.

    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
     hoặc
    0.89
     alebo
    0.88
     nebo
    0.83
     ಅಥವಾ
    0.81
     veya
    0.80
    または
    0.76
     または
    0.76
     或
    0.73
     või
    0.71
     किंवा
    0.71
    POSITIVE LOGITS
    打造
    0.84
     extravaganza
    0.80
     coffers
    0.79
    如今
    0.77
     extraordinaire
    0.77
     હવે
    0.76
     unrivalled
    0.75
     unapolog
    0.75
     तकरीबन
    0.75
     reigns
    0.74
    Activations Density 0.081%

    No Known Activations