© 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. 7322
    Prev
    Next
    INDEX
    Explanations

    in or after list

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

    The neuron fires strongly on the very first significant content word (the topic‐introducing word) of each text segment.

    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
     Decisions
    0.65
     February
    0.62
    ō
    0.62
     RO
    0.61
     LGBTQ
    0.61
    ―
    0.61
     $\$
    0.61
     $\
    0.60
     COVID
    0.59
    vero
    0.59
    POSITIVE LOGITS
    ﺨ
    1.01
    胫
    1.00
    ﺘ
    0.96
    ﯿ
    0.94
     zprac
    0.92
    FromThe
    0.92
     tepung
    0.91
     baddies
    0.90
     beauties
    0.87
     asos
    0.87
    Activations Density 0.001%

    No Known Activations