© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60051
    Prev
    Next
    INDEX
    Explanations

    New Jersey, college, Attorney General

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

    The main thing this neuron does is detect references to gambling—especially mentions of sports betting and related wagering terms.

    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
    իդ
    -1.04
    opheles
    -1.02
    Öff
    -1.02
    Rujukan
    -0.99
    Халы
    -0.98
     yağı
    -0.97
    影响
    -0.95
    bieter
    -0.93
     isoliert
    -0.93
    nteral
    -0.93
    POSITIVE LOGITS
     NJ
    1.19
     in
    1.05
    }+$
    1.03
     Delaware
    0.97
    ！"
    0.95
     nj
    0.94
    hyung
    0.94
     NYC
    0.93
    bkg
    0.92
     arkiv
    0.92
    Activations Density 0.173%

    No Known Activations