© 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. 6048
    Prev
    Next
    INDEX
    Explanations

    The neuron is selectively activating on numeric expressions (quantities, statistics, and numbers) 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
    半径
    0.71
     കമ്പ
    0.69
     היה
    0.66
     Daarnaast
    0.66
    ˉ
    0.65
     tambien
    0.64
    
    0.64
     vielfält
    0.64
     সংশ্লিষ্ট
    0.63
    羅
    0.63
    POSITIVE LOGITS
     ông
    0.93
     oorlog
    0.90
     Ông
    0.88
     Oncology
    0.86
     oyun
    0.86
     の
    0.85
     otorg
    0.83
     oscuro
    0.82
     ogrom
    0.82
     온도
    0.82
    Activations Density 2.852%

    No Known Activations