© 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. 10-GEMMASCOPE-RES-131K
    4. 127245
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    The neuron responds to numeric values with decimal points.

    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
     vreme
    -1.34
    たと
    -1.32
    monės
    -1.29
     ngào
    -1.29
    romole
    -1.29
     recurrir
    -1.28
    .
    -1.28
    ými
    -1.28
     from
    -1.24
     deseado
    -1.23
    POSITIVE LOGITS
     for
    3.50
     when
    1.82
    「
    1.78
     «
    1.70
     „
    1.61
     to
    1.49
     forKey
    1.48
    rceil
    1.48
     для
    1.46
     برای
    1.41
    Activations Density 0.091%

    No Known Activations