© 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. 1986
    Prev
    Next
    INDEX
    Explanations

    programming keywords and functions

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

    This neuron activates strongly on programming API calls and function or method names in code 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_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
                      
    0.54
     sach
    0.53
     riche
    0.53
     Richards
    0.51
     orange
    0.50
     tutte
    0.50
     rise
    0.50
     Pav
    0.49
     ：
    0.49
    1
    0.49
    POSITIVE LOGITS
    (...)
    0.61
     gør
    0.61
    ně
    0.59
    ="..."
    0.58
    rather
    0.57
    offers
    0.57
    posing
    0.57
    trk
    0.56
     రూపొ
    0.56
     делает
    0.56
    Activations Density 0.010%

    No Known Activations