© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68664
    Prev
    Next
    INDEX
    Explanations

    age ranges

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

    The neuron activates on numerical digits and numeric expressions (e.g. ages, ranges, percentages) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     treu
    -1.41
    '"
    -1.32
     "
    -1.24
    neither
    -1.23
     $^{\
    -1.23
     itin
    -1.20
    '')
    -1.18
     mouseY
    -1.17
     solidar
    -1.17
    "'
    -1.17
    POSITIVE LOGITS
    0
    1.48
    4
    1.41
    2
    1.39
     when
    1.31
     young
    1.27
    5
    1.27
     When
    1.27
     cuando
    1.26
    1
    1.25
     edilir
    1.21
    Activations Density 0.041%

    No Known Activations