© 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. 22-GEMMASCOPE-RES-131K
    7. 128197
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting geographic location names (e.g. city or country names) and their associated numeric address elements in academic affiliation lines.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    city names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    july
    -1.21
     was
    -1.14
    était
    -1.01
     bergen
    -0.98
    \.
    -0.96
    $
    -0.95
     tämän
    -0.95
    IENT
    -0.95
     dianteiro
    -0.94
    ?
    -0.93
    POSITIVE LOGITS
    选举
    1.05
    Probl
    1.02
     Վեր
    1.02
    んじゃ
    1.00
    vedades
    0.99
    较高
    0.99
    他们在
    0.98
     démission
    0.98
    你了
    0.98
    诱惑
    0.94
    Activations Density 0.010%

    No Known Activations