© 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. 22-GEMMASCOPE-RES-131K
    7. 130117
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly responsive to numerical and quantitative expressions (numbers, measurements, distances, statistics, units, etc.).

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

    specific topics and entities

    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
    autres
    -0.89
     steadfast
    -0.84
     with
    -0.83
    行
    -0.83
    过来了
    -0.83
    金币
    -0.81
    iros
    -0.81
     servire
    -0.80
    ENAME
    -0.79
    ága
    -0.79
    POSITIVE LOGITS
    дей
    0.98
     restTemplate
    0.92
     vestidos
    0.92
     работа
    0.91
    ਰਾ
    0.90
     empaque
    0.90
     Если
    0.88
     indique
    0.88
     récentes
    0.87
     здесь
    0.86
    Activations Density 0.231%

    No Known Activations