© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59209
    Prev
    Next
    INDEX
    Explanations

    Citi, Citigroup, Citibank, bank entities

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

    The neuron specifically detects mentions of the financial institution “Citi,” as in “Citi group,” “Citi bank,” or similar Citigroup references.

    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
    ruptedException
    -2.47
    尨
    -2.44
    媄
    -2.36
    冖
    -2.19
     дерева
    -2.16
     reconocida
    -2.09
     considéré
    -2.09
     encontraron
    -2.08
    ).
    -2.05
    もちろん
    -2.02
    POSITIVE LOGITS
    (
    3.02
    {
    2.61
    𖥧
    2.42
    ྜ
    2.41
    龵
    2.28
    是我们
    2.22
    
    2.11
     This
    2.08
    ſſel
    2.03
    檯
    2.02
    Activations Density 0.001%

    No Known Activations