© 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. 10-GEMMASCOPE-RES-131K
    7. 9442
    Prev
    Next
    INDEX
    Explanations

    in, after, from, as

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

    This neuron detects numeric measurement tokens (especially decimal and other numbers) in technical or scientific 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_10/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
    Even
    -1.70
    Quite
    -1.52
    Many
    -1.48
     أيض
    -1.48
     enamorado
    -1.47
    You
    -1.46
    We
    -1.45
    Before
    -1.44
    Every
    -1.44
    Numerous
    -1.42
    POSITIVE LOGITS
     about
    1.59
     andere
    1.44
     다른
    1.40
     in
    1.30
     ícone
    1.29
     no
    1.28
    VERTISEMENT
    1.27
     to
    1.26
     wła
    1.26
    gibt
    1.25
    Activations Density 0.122%

    No Known Activations