© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3495
    Prev
    Next
    INDEX
    Explanations

    city website urls

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

    This neuron fires strongly on the first substantive token of a new sentence or paragraph.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     হলিউ
    0.84
     analyte
    0.82
     ट्रंप
    0.82
    体积
    0.82
     QuickBooks
    0.79
     ഇന്ത്യ
    0.77
     Obamacare
    0.77
    愆
    0.76
    діть
    0.76
     Америки
    0.75
    POSITIVE LOGITS
     Stadt
    1.26
     gemeente
    1.17
     Centro
    1.13
     municipal
    1.11
     Municipal
    1.11
     Municipality
    1.10
     Firma
    1.07
     Ayuntamiento
    1.06
     Kultur
    1.05
     Kult
    1.03
    Activations Density 0.448%

    No Known Activations