© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7367
    Prev
    Next
    INDEX
    Explanations

    geopolitical conflict and strategy

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

    The neuron detects words that refer to policy negotiations, demands, and regulatory actions.

    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
     (
    1.34
    (
    1.05
    /
    1.02
     /
    0.93
     (=
    0.89
    においても
    0.88
    においては
    0.87
     (?)
    0.85
     HIPAA
    0.85
     (\
    0.84
    POSITIVE LOGITS
     تريد
    1.09
    <unused689>
    1.02
    <unused276>
    1.02
    <unused723>
    1.02
    <unused287>
    1.00
     нужны
    0.98
    <unused247>
    0.96
    <unused662>
    0.95
    <unused274>
    0.95
     لكن
    0.95
    Activations Density 0.001%

    No Known Activations