© 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. 1868
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric measurements (e.g. temperatures, quantities, percentages) and their associated units.

    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
    riages
    0.61
     Chaucer
    0.58
    彝
    0.57
    穀
    0.56
    🛤
    0.56
     Kant
    0.54
     افغانستان
    0.54
     ResponseEntity
    0.54
     ప్రే
    0.53
    ższej
    0.52
    POSITIVE LOGITS
     swim
    2.98
     swimming
    2.92
     swims
    2.92
     swimmers
    2.88
     Swim
    2.83
     underwater
    2.80
     Swimming
    2.78
    🏊
    2.77
    Swim
    2.72
     swimmer
    2.70
    Activations Density 1.189%

    No Known Activations