© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4063
    Prev
    Next
    INDEX
    Explanations

    located in

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

    The neuron primarily fires on the word “located” (and its capitalized form “Located”), marking sentences that state a geographical placement.

    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_24_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
    ur
    0.93
     femora
    0.92
     lalu
    0.91
    导出
    0.91
    其余
    0.87
     progenitors
    0.86
    試合
    0.84
    诬
    0.84
     menampilkan
    0.84
     précédentes
    0.83
    POSITIVE LOGITS
    north
    1.45
    ą
    1.20
    te
    1.10
    henburg
    1.09
    located
    1.07
     недалеко
    1.07
     شمال
    1.02
     south
    0.99
     nörd
    0.99
    sunny
    0.98
    Activations Density 0.021%

    No Known Activations