© 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. 34-GEMMASCOPE-RES-131K
    7. 31190
    Prev
    Next
    INDEX
    Explanations

    percentages and proportions

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

    The neuron is highly activated by numeric expressions—especially standalone numbers, percentages, and counts.

    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
     אב
    -0.75
    oges
    -0.73
    落实
    -0.71
    三十
    -0.70
    四十
    -0.70
     \$
    -0.69
    ৮
    -0.68
    udnio
    -0.68
    raszam
    -0.66
    ७
    -0.66
    POSITIVE LOGITS
     ۰
    1.37
     (.
    1.30
    =.
    1.01
    (.
    0.96
     ۱
    0.95
     <.
    0.94
     infinitesimal
    0.90
     .
    0.89
     fractions
    0.88
     (<
    0.87
    Activations Density 0.114%

    No Known Activations