© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9869
    Prev
    Next
    INDEX
    Explanations

    Europe and other continents

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

    The neuron detects breadcrumb‐style navigation separators (e.g. “>” or “\”) in page paths.

    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
    skew
    0.60
    req
    0.55
    铝
    0.55
    ვ
    0.54
    тка
    0.54
    akka
    0.54
    oplus
    0.52
    wakeup
    0.52
    sleep
    0.52
    화
    0.51
    POSITIVE LOGITS
     Yankees
    0.66
     Ulster
    0.65
     আনি
    0.64
     wonderland
    0.64
     Lernen
    0.64
     Enchant
    0.62
     Dime
    0.61
     Irene
    0.61
     locomotives
    0.61
     enchanted
    0.60
    Activations Density 0.001%

    No Known Activations