© 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. 60716
    Prev
    Next
    INDEX
    Explanations

    cosine and sine mathematical expressions

    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
    sinh
    -0.98
    tan
    -0.88
     quà
    -0.87
     sinh
    -0.81
    arcs
    -0.81
    timents
    -0.79
    collect
    -0.77
     schw
    -0.77
    thet
    -0.77
    พระ
    -0.75
    POSITIVE LOGITS
    cos
    2.08
     cos
    2.08
     cosine
    1.90
    Cos
    1.70
     Cos
    1.68
    cosine
    1.31
    COS
    1.29
     COS
    1.29
     cost
    1.28
    icos
    1.22
    Activations Density 0.015%

    No Known Activations