© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32893
    Prev
    Next
    INDEX
    Explanations

    cosine function in mathematics

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

    The neuron fires on occurrences of the trig function “cos” (i.e. cosine) within 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
     to
    -1.56
    鼍
    -1.45
     ۱۰
    -1.38
    跸
    -1.37
    砗
    -1.32
    llllll
    -1.31
    浒
    -1.30
    rrrr
    -1.30
    鬟
    -1.30
    fusions
    -1.29
    POSITIVE LOGITS
     Befes
    1.41
    }$
    1.31
     großen
    1.27
     varanda
    1.25
    JvmStatic
    1.24
     koska
    1.21
     uncanny
    1.17
     flir
    1.13
     weiteren
    1.13
     работе
    1.13
    Activations Density 0.002%

    No Known Activations