© 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. 102750
    Prev
    Next
    INDEX
    Explanations

    on the verge/brink/edge/cusp/precipice

    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
    ografija
    -0.75
    GD
    -0.71
     太郎
    -0.69
     وات
    -0.69
    ंडल
    -0.69
    alle
    -0.67
     Ella
    -0.66
     Warrior
    -0.66
    ennon
    -0.66
    owego
    -0.65
    POSITIVE LOGITS
     verge
    2.98
     brink
    2.95
     edge
    2.41
     cusp
    2.19
     on
    1.99
     precipice
    1.96
    边缘
    1.92
     threshold
    1.86
    edge
    1.79
     Verge
    1.73
    Activations Density 0.049%

    No Known Activations