© 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. 34-GEMMASCOPE-RES-131K
    7. 117748
    Prev
    Next
    INDEX
    Explanations

    compact topological spaces

    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
     strictement
    -0.79
    onar
    -0.79
    減
    -0.73
    ufficio
    -0.72
    ترل
    -0.71
    报
    -0.70
    foobar
    -0.70
    aluminum
    -0.70
     bleus
    -0.69
     Kirkwood
    -0.69
    POSITIVE LOGITS
     spaces
    1.21
     topological
    1.18
     topo
    1.05
     topology
    1.01
     Spaces
    1.00
     separation
    0.99
    spaces
    0.97
     Haus
    0.96
     Topology
    0.95
    topo
    0.91
    Activations Density 0.054%

    No Known Activations