© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129567
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numerical measurements and quantity expressions (e.g. numbers with units, durations, counts, and other numeric data).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    then followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     WAIT
    -0.84
    alumnos
    -0.84
    Leave
    -0.82
    resting
    -0.82
     pauses
    -0.81
    等待
    -0.80
    ując
    -0.80
     Leave
    -0.80
    più
    -0.80
    いてる
    -0.80
    POSITIVE LOGITS
     then
    1.91
     when
    1.20
    Then
    1.04
     Then
    0.98
     thereafter
    0.89
     later
    0.87
    然后
    0.84
    ATTACK
    0.84
     затем
    0.84
     attack
    0.83
    Activations Density 0.043%

    No Known Activations