© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3027
    Prev
    Next
    INDEX
    Explanations

    aid to countries

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

    The neuron activates on numeric expressions—especially years, quantities, and other numbers—within 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
    у
    0.61
    NSLog
    0.58
    punctuation
    0.55
    horsepower
    0.55
    用到
    0.55
    ロング
    0.55
    例子
    0.54
     Stiffness
    0.54
    뻥
    0.54
    unction
    0.54
    POSITIVE LOGITS
     Myanmar
    0.85
     Venezuela
    0.84
     Ukraine
    0.83
     Iraq
    0.82
     Chile
    0.82
     Afghanistan
    0.81
     India
    0.80
     neoliberal
    0.77
     Syria
    0.77
     Russia
    0.76
    Activations Density 0.006%

    No Known Activations