© 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. 21017
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas

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

    The neuron is triggered by numeric literals and number-containing tokens 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_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
     What
    -1.90
     to
    -1.83
     only
    -1.81
     This
    -1.74
    *
    -1.72
     as
    -1.71
     September
    -1.60
     December
    -1.59
     In
    -1.58
    o
    -1.58
    POSITIVE LOGITS
     idiota
    1.55
     relig
    1.51
     Wanita
    1.45
     geng
    1.45
     Keluarga
    1.45
     plak
    1.45
    Ꮘ
    1.45
     Juventud
    1.43
    螄
    1.42
    ᚷ
    1.41
    Activations Density 0.022%

    No Known Activations