© 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. 34532
    Prev
    Next
    INDEX
    Explanations

    order followed by technical terms

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

    This neuron detects the term “order” (as in “first order,” “second order,” “higher order,” etc.) when used to classify or describe the mathematical order of objects or equations.

    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
     third
    -1.41
     second
    -1.33
    third
    -1.26
    Third
    -1.24
    Second
    -1.23
     Third
    -1.21
     Second
    -1.19
    second
    -1.09
    第一
    -1.06
    SECOND
    -1.05
    POSITIVE LOGITS
     approximation
    0.88
     polynomial
    0.84
     accurate
    0.83
    accurate
    0.81
    早速
    0.76
     ytterligare
    0.76
    Beskrivelse
    0.74
     accuracy
    0.72
     särskilt
    0.71
     effects
    0.71
    Activations Density 0.037%

    No Known Activations