© 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. 118395
    Prev
    Next
    INDEX
    Explanations

    edge or edges

    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
    лера
    -0.78
    劳动
    -0.75
    리는
    -0.72
    uhnya
    -0.71
    Ponte
    -0.71
    瓤
    -0.71
     fouling
    -0.71
    atalytic
    -0.70
     Tavares
    -0.70
    garia
    -0.70
    POSITIVE LOGITS
     edge
    1.80
     edges
    1.59
    edge
    1.51
    edges
    1.45
     Edge
    1.39
    Edge
    1.34
     gradient
    1.30
    Edges
    1.27
     Sob
    1.23
    EDGE
    1.21
    Activations Density 0.022%

    No Known Activations