© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73549
    Prev
    Next
    INDEX
    Explanations

    variable 'z' in math expressions

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

    The neuron consistently fires on the mathematical variable “z” (i.e. occurrences of the token z in formulae).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    n
    -3.20
    t
    -2.95
    al
    -2.91
    のだが
    -2.81
    a
    -2.73
     måde
    -2.56
    軔
    -2.50
    in
    -2.47
     problemer
    -2.45
    :^{
    -2.44
    POSITIVE LOGITS
    '
    3.66
    "
    2.83
    -
    2.81
    I
    2.80
     of
    2.64
     \
    2.55
     i
    2.44
    *
    2.41
    。"
    2.36
    \
    2.36
    Activations Density 0.017%

    No Known Activations