© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13114
    Prev
    Next
    INDEX
    Explanations

    DataFrame methods and attributes

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

    This neuron lights up on code‐like tokens and numeric data entries (e.g. R function names, brackets, numbers, and variable references) rather than ordinary text.

    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
     Happened
    0.59
    imut
    0.58
    RETURNS
    0.57
     Returns
    0.54
    OrderID
    0.53
    溢
    0.52
    Utf
    0.52
    prd
    0.52
    idega
    0.51
    Returns
    0.51
    POSITIVE LOGITS
     locating
    0.60
     subgroups
    0.59
     locate
    0.58
    iloc
    0.57
    [["
    0.54
    hexahydro
    0.54
     loc
    0.52
     subsets
    0.52
     ट
    0.52
    [['
    0.52
    Activations Density 0.001%

    No Known Activations