© 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. 128291
    Prev
    Next
    INDEX
    Explanations

    Fargo, covariates, Farm, Argo

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

    The neuron strongly activates on the specific place name “Fargo.”

    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
    缡
    -2.88
    🫃
    -2.83
    </h4>
    -2.78
     magnificent
    -2.73
    
    -2.70
     чёр
    -2.67
    enablog
    -2.66
    氿
    -2.59
    簠
    -2.58
     tremendous
    -2.55
    POSITIVE LOGITS
    ↵↵
    3.25
    ၉
    2.16
     Fargo
    2.09
    需要
    2.05
    寕
    1.95
     penampilan
    1.95
    錞
    1.92
     lahir
    1.91
    獁
    1.89
    峩
    1.86
    Activations Density 0.001%

    No Known Activations