© 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. 6143
    Prev
    Next
    INDEX
    Explanations

    comparisons involving Earth

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

    The neuron strongly activates on references to the Earth as a scientific subject—e.g. “Earth,” “Earth’s systems,” numerical ages of the planet, and other Earth‐science terms.

    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
     अभिक्रिया
    0.57
    測定
    0.55
    秤
    0.54
    relativistic
    0.53
    spiritual
    0.52
     ஏக்க
    0.51
    農
    0.51
    周囲
    0.50
    isValid
    0.50
    agricultural
    0.50
    POSITIVE LOGITS
     système
    0.64
     Systems
    0.62
    ysteem
    0.62
     System
    0.61
     systèmes
    0.61
     SYS
    0.61
     hệ
    0.60
     SYSTEMS
    0.59
     Wechsel
    0.59
     Système
    0.59
    Activations Density 0.013%

    No Known Activations