© 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. 4000
    Prev
    Next
    INDEX
    Explanations

    javascript code blocks

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

    This neuron activates on parentheses tokens—especially “()” or parentheses around function or method names—i.e. it’s detecting parenthetical or function‐call notation.

    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
    以及
    0.55
    一丝
    0.51
    贮
    0.51
     selalu
    0.50
    mechan
    0.48
     Realt
    0.48
    傢
    0.48
    Mechan
    0.48
    并将
    0.48
    将被
    0.48
    POSITIVE LOGITS
     muerte
    0.57
     loadChildren
    0.52
     발표
    0.51
     自己
    0.49
     dopo
    0.49
     நானும்
    0.48
     이러
    0.48
     死
    0.48
     入
    0.47
     дети
    0.47
    Activations Density 0.001%

    No Known Activations