© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9063
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily activates on decimal numbers (floating-point numerical values) embedded in the 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
     retention
    0.75
     thermal
    0.68
    :
    0.67
     deple
    0.65
     transverse
    0.65
     tensile
    0.65
     contaminant
    0.65
     caries
    0.64
     pyrite
    0.64
     tassels
    0.63
    POSITIVE LOGITS
     정부
    0.81
     사람들이
    0.77
     capaces
    0.76
     governo
    0.75
     hükü
    0.75
    VSLU
    0.75
    ì
    0.74
     이날
    0.73
     지난해
    0.73
     સરકાર
    0.73
    Activations Density 0.000%

    No Known Activations