© 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. 60808
    Prev
    Next
    INDEX
    Explanations

    convex and concave functions

    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
     KLE
    -0.75
     sobbing
    -0.72
    ppie
    -0.71
     visitas
    -0.71
     Thời
    -0.70
     shortening
    -0.70
    אָ
    -0.67
     Среди
    -0.67
    ánto
    -0.65
     visites
    -0.65
    POSITIVE LOGITS
     convex
    1.55
     concave
    1.30
    convex
    1.27
     Convex
    1.08
    Convex
    1.06
     Moreau
    0.94
     function
    0.93
    函数
    0.92
     functions
    0.90
     penal
    0.89
    Activations Density 0.028%

    No Known Activations