© 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. 7678
    Prev
    Next
    INDEX
    Explanations

    //@version=5

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

    The neuron detects numerical measurements—especially decimal figures (e.g. distances, ages, percentages, citation years)—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_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
    ing
    0.85
    ようになる
    0.79
    м
    0.77
    ry
    0.77
    daki
    0.77
    ed
    0.76
    ようになって
    0.75
    down
    0.75
    댄
    0.75
    ة
    0.74
    POSITIVE LOGITS
     PEOPLE
    0.81
     Aquatic
    0.79
     ASGI
    0.79
     Conseils
    0.78
     narratives
    0.77
     océ
    0.76
    STATEMENT
    0.75
     genotypes
    0.75
     horaires
    0.75
     ★★
    0.75
    Activations Density 0.000%

    No Known Activations