© 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. 4864
    Prev
    Next
    INDEX
    Explanations

    those who

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

    The neuron responds to numeric tokens, especially floating‐point numbers (numbers containing a decimal point).

    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
    LL
    1.10
    CTION
    1.10
    る
    1.09
    a
    1.09
    um
    1.08
    tuples
    1.07
    ة
    1.05
    会导致
    1.05
    IENCE
    1.03
     مؤرشف
    1.00
    POSITIVE LOGITS
     pesky
    1.34
    zelfde
    1.29
    єї
    1.09
     glist
    0.97
    不久
    0.92
    습니다
    0.91
    های
    0.91
    וה
    0.89
     attentively
    0.89
    肐
    0.89
    Activations Density 0.033%

    No Known Activations