© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8200
    Prev
    Next
    INDEX
    Explanations

    etched stone

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

    The neuron activates on technical physics or engineering terms describing forces, motion, and related scalar/vector quantities.

    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
    。\
    0.86
    。</
    0.84
    。
    0.81
     The
    0.78
     Göttingen
    0.75
    ।
    0.75
     Gazi
    0.73
     Czę
    0.71
     České
    0.71
     Telangana
    0.70
    POSITIVE LOGITS
    ෲ
    0.71
    thru
    0.65
     উহা
    0.63
     thru
    0.62
     leafs
    0.62
    原创
    0.61
    <eos>
    0.61
    下さい
    0.60
     উহার
    0.60
     이라고
    0.59
    Activations Density 0.093%

    No Known Activations