© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45654
    Prev
    Next
    INDEX
    Explanations

    Grace, Valencia, Clanton

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

    The neuron fires strongly on capitalized tokens that are parts of geographic place names (towns, regions, and other location names).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    </h1>
    -1.53
    tivität
    -1.39
     -----
    -1.38
    䜣
    -1.37
     ומ
    -1.35
    unicaciones
    -1.34
    یان
    -1.33
    њу
    -1.32
    zation
    -1.31
    钐
    -1.30
    POSITIVE LOGITS
    ）、
    1.62
     계획
    1.51
        
    1.50
    zędu
    1.38
    0
    1.36
    ”),
    1.34
     giàu
    1.27
       
    1.26
    The
    1.25
    izop
    1.25
    Activations Density 0.734%

    No Known Activations