© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68272
    Prev
    Next
    INDEX
    Explanations

    apparatus and equipment

    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
     Вода
    -1.05
    formData
    -1.02
     their
    -0.99
    дія
    -0.91
    th
    -0.91
    🤾
    -0.90
     substation
    -0.90
     проє
    -0.88
    b
    -0.88
    おかげ
    -0.87
    POSITIVE LOGITS
     equipment
    1.66
     devices
    1.59
     device
    1.46
     portable
    1.43
     apparatus
    1.41
     purchase
    1.26
    téri
    1.26
    鼩
    1.23
     instruments
    1.23
    댈
    1.21
    Activations Density 0.204%

    No Known Activations