© 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. 48411
    Prev
    Next
    INDEX
    Explanations

    #define and \mathrm

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

    The neuron responds to numeric literals containing decimal points—that is, tokens representing numbers with fractions.

    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
     with
    -2.64
    There
    -2.05
    It
    -2.03
     WITH
    -1.92
    The
    -1.91
     new
    -1.88
     There
    -1.88
     on
    -1.88
     in
    -1.87
     use
    -1.84
    POSITIVE LOGITS
     willen
    1.90
     dieß
    1.80
     ation
    1.74
     alip
    1.64
     nying
    1.63
     bringe
    1.56
     starten
    1.56
     ſever
    1.55
     konfig
    1.55
    鵙
    1.54
    Activations Density 0.023%

    No Known Activations