© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12184
    Prev
    Next
    INDEX
    Explanations

    history and geography

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

    The neuron is triggered by mentions of formal school subjects or academic disciplines (e.g. history, geography, literature, sciences, civics, foreign languages, social studies, etc.).

    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
     pharmacological
    0.64
     मॉडलिंग
    0.62
     instrumentation
    0.61
     pharmaceutical
    0.60
     Pharmac
    0.59
    Š
    0.59
     лечения
    0.59
     ဆ
    0.59
     Pharmaceutical
    0.58
     cryptographic
    0.58
    POSITIVE LOGITS
    Geography
    1.15
     Geography
    1.12
     geography
    1.11
    Histor
    1.02
     Histor
    1.01
     historians
    0.99
    地理
    0.98
     historian
    0.95
     histori
    0.94
     Civilization
    0.92
    Activations Density 0.084%

    No Known Activations