© 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. 10384
    Prev
    Next
    INDEX
    Explanations

    years, overall, complex, stress, Wild

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

    The neuron is highly responsive to numeric expressions (especially decimal numbers) and the surrounding terms, i.e. it flags passages that present quantitative data.

    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
    lc
    0.89
    ز
    0.78
    ব
    0.73
     команду
    0.71
    تو
    0.71
    tl
    0.70
    تن
    0.70
    tors
    0.69
    lines
    0.69
    slot
    0.68
    POSITIVE LOGITS
     Cette
    0.92
     І
    0.92
    的数据
    0.91
    Voir
    0.91
     Aussi
    0.90
    Cette
    0.90
    Namun
    0.89
    Essex
    0.88
    І
    0.86
    ian
    0.85
    Activations Density 0.000%

    No Known Activations