© 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. 22-GEMMASCOPE-RES-131K
    7. 9513
    Prev
    Next
    INDEX
    Explanations

    trigonometric functions: sin, cos

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is detecting occurrences of trigonometric function calls (especially “sin(” and “cos(”) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     morti
    -1.13
     diabe
    -0.99
     tenuto
    -0.98
    kkal
    -0.98
    EMAS
    -0.97
     GARANT
    -0.97
    太多
    -0.96
     bayer
    -0.96
    ⓖ
    -0.96
    հ
    -0.95
    POSITIVE LOGITS
     or
    1.35
     hacían
    1.15
     at
    1.06
     между
    1.02
     дочь
    0.98
     или
    0.97
     oficinas
    0.97
     six
    0.96
     by
    0.95
     as
    0.94
    Activations Density 0.006%

    No Known Activations