© 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. 153
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on long, multi‐paragraph blocks of user‐written forum or commentary text rather than on short snippets.

    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
     tomonidan
    0.34
     tarafından
    0.29
     இருந்து
    0.27
     Serien
    0.27
     J
    0.25
    煒
    0.25
     দেখিয়া
    0.24
     Mga
    0.24
    0
    0.24
     โดย
    0.24
    POSITIVE LOGITS
     atop
    0.64
     squarely
    0.48
     on
    0.48
     firmly
    0.47
     trên
    0.47
     onto
    0.46
     prominently
    0.45
     alongside
    0.45
     snugly
    0.45
     на
    0.43
    Activations Density 1.274%

    No Known Activations