© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1066
    Prev
    Next
    INDEX
    Explanations

    pricing strategy

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

    The neuron is specialized to detect numeric quantities (numbers, counts, percentages, etc.) 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_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
     ذریع
    0.99
    ።
    0.79
     কেননা
    0.75
    %。
    0.74
    ا۔
    0.74
    ()}.
    0.73
    ഇ
    0.73
    ے۔
    0.72
    %),
    0.71
    ！！
    0.70
    POSITIVE LOGITS
     is
    2.16
     has
    2.11
     differs
    2.02
     becomes
    1.95
     appears
    1.88
     depends
    1.87
     varies
    1.86
     arises
    1.84
     seems
    1.83
     comes
    1.82
    Activations Density 2.248%

    No Known Activations