© 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. 34-GEMMASCOPE-RES-131K
    7. 65881
    Prev
    Next
    INDEX
    Explanations

    nature and education centers

    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_34/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
     termé
    -0.90
    场面
    -0.87
    カビ
    -0.85
    钞
    -0.85
    %>
    -0.84
    ψ
    -0.84
    创意
    -0.82
     anthropologists
    -0.82
    帮
    -0.82
    convention
    -0.81
    POSITIVE LOGITS
     naturalist
    1.63
     nature
    1.46
     Nature
    1.38
     educational
    1.36
     education
    1.34
    Nature
    1.31
     Naturalist
    1.28
     educate
    1.22
     hikes
    1.19
     trail
    1.16
    Activations Density 0.033%

    No Known Activations