© 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. 73821
    Prev
    Next
    INDEX
    Explanations

    function $f$ or variable $X$ after opening parenthesis

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

    The neuron is a detector for numeric tokens (digits, numbers, or variables with numeric subscripts/superscripts) 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_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
     lograron
    -1.38
    banez
    -1.34
     where
    -1.34
    postolic
    -1.29
    vermectin
    -1.27
    ḿ
    -1.27
     których
    -1.23
    friger
    -1.23
     querían
    -1.22
     comenzaron
    -1.21
    POSITIVE LOGITS
     is
    3.52
     was
    2.27
     has
    2.17
     isn
    2.11
     cannot
    1.95
     wasn
    1.95
     can
    1.66
     =
    1.62
     could
    1.62
     doesn
    1.59
    Activations Density 0.068%

    No Known Activations