© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7690
    Prev
    Next
    INDEX
    Explanations

    numbers followed by numbers

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

    The neuron activates on numeric tokens—especially multi‐digit values and decimal numbers—i.e. it’s looking for numerical measurements.

    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_24_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
    。
    0.86
    }{\
    0.76
    boldsymbol
    0.69
    ।
    0.68
    ì
    0.65
    姓
    0.63
    庄
    0.63
    은
    0.63
    \
    0.62
    กับ
    0.61
    POSITIVE LOGITS
     introduit
    0.77
     autres
    0.74
     fournit
    0.71
     linguaggio
    0.70
     instantiation
    0.70
     ноутбу
    0.70
    ufieurs
    0.69
     spazio
    0.68
    ຈັດສົ່ງ
    0.68
     distributions
    0.67
    Activations Density 0.011%

    No Known Activations