© 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. 113914
    Prev
    Next
    INDEX
    Explanations

    Santiago, James, Cag, Jaco, Gago

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

    The neuron fires almost exclusively on the place name “Santiago.”

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     collage
    -2.53
     spô
    -2.50
    *
    -2.47
    歘
    -2.41
    劼
    -2.41
    aphne
    -2.36
     barring
    -2.33
     možnosti
    -2.31
    
    -2.31
     jejich
    -2.23
    POSITIVE LOGITS
    ]
    2.52
    ↵
    2.50
    s
    2.42
    ization
    2.25
     is
    2.22
     sebagai
    2.20
     própri
    2.19
     в
    2.11
    结语
    2.09
    ities
    2.06
    Activations Density 0.001%

    No Known Activations