© 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. 2263
    Prev
    Next
    INDEX
    Explanations

    immune cells

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

    This neuron is tuned to pick out numeric tokens—such as prices, measures, article or legal citation numbers, and other digit-based references.

    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
    這些
    0.66
    喏
    0.65
    কিছু
    0.64
     있다고
    0.62
     وهذا
    0.61
    ផង
    0.61
    始め
    0.60
    ത്തിന്റെയും
    0.59
    㤟
    0.57
    叕
    0.57
    POSITIVE LOGITS
    ∶
    0.67
    îte
    0.64
    
    0.64
     ∼
    0.61
     colesterol
    0.59
     leukaemia
    0.58
     τη
    0.55
     wildlife
    0.55
    ⩽
    0.55
     glycerol
    0.54
    Activations Density 0.459%

    No Known Activations