© 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. 3381
    Prev
    Next
    INDEX
    Explanations

    and providing

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

    The neuron fires on the comma that closes off an initial or parenthetical clause (e.g. after “For members of…,” “In the NFL,” “In many ways,” etc.), marking the end of an introductory or non‐restrictive phrase.

    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
     таксама
    0.91
     також
    0.85
     quelquefois
    0.77
     innych
    0.76
     supaya
    0.74
     incluem
    0.74
     drugih
    0.73
     mischiev
    0.72
     также
    0.72
     khusus
    0.71
    POSITIVE LOGITS
    this
    0.99
    这场
    0.91
     this
    0.90
     THIS
    0.89
     сегодняшний
    0.88
     이번
    0.88
    今回の
    0.84
     новый
    0.78
     এবারের
    0.78
    This
    0.77
    Activations Density 0.264%

    No Known Activations