© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13816
    Prev
    Next
    INDEX
    Explanations

    claim, method, case, SQL, BULK INSERT

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

    The neuron is primarily activated by numerical tokens (digits, figure/step/claim numbers, and numeric subscripts) in the technical document.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     طالب
    0.56
     TAN
    0.56
     modelli
    0.56
     LIE
    0.56
    
    0.56
     Donne
    0.56
     Bankr
    0.55
    精确
    0.55
    νης
    0.55
     Artis
    0.55
    POSITIVE LOGITS
    cmake
    0.68
    avelmente
    0.58
    CMake
    0.57
    ```
    0.56
    dr
    0.56
    def
    0.54
    `:
    0.54
    KeyDown
    0.53
    紫外線
    0.53
    JOIN
    0.52
    Activations Density 0.005%

    No Known Activations