© 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. 31-GEMMASCOPE-2-RES-16K
    7. 608
    Prev
    Next
    INDEX
    Explanations

    prefixes followed by specific words

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

    The neuron reliably activates on proper names and other named-entity tokens—especially author or contributor names in bylines and citations.

    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_31_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
    W
    0.51
     t
    0.49
     b
    0.46
     AND
    0.46
     Messi
    0.45
    U
    0.45
     Skywalker
    0.45
     g
    0.45
     gaan
    0.44
     Hadid
    0.44
    POSITIVE LOGITS
    杍
    0.41
    躹
    0.39
    竝
    0.38
    нициа
    0.38
    indazol
    0.38
    急速
    0.37
    靔
    0.35
    夻
    0.34
    pulsewidth
    0.34
    कार्यक्रम
    0.34
    Activations Density 0.521%

    No Known Activations