© 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. 21783
    Prev
    Next
    INDEX
    Explanations

    Newark Athlete, Secondary Menu

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

    This neuron detects floating‐point numeric literals (decimal numbers with fractional parts).

    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
     their
    -2.63
    {
    -2.14
     only
    -2.05
     a
    -1.77
    ჻
    -1.75
    unjungi
    -1.68
     adecu
    -1.67
    They
    -1.63
     custa
    -1.63
     any
    -1.56
    POSITIVE LOGITS
     of
    1.60
    踅
    1.48
    zulegen
    1.46
    茕
    1.45
     alrededores
    1.44
    di
    1.42
     而
    1.42
    ⼥
    1.41
    genen
    1.40
    趿
    1.40
    Activations Density 0.002%

    No Known Activations