© 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. 119583
    Prev
    Next
    INDEX
    Explanations

    numerical values or sequences

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

    The neuron selectively activates on decimal numbers (values containing a point) in 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
     to
    -1.98
    婓
    -1.86
     Hinsicht
    -1.59
    XVII
    -1.55
     SimpleName
    -1.53
    伈
    -1.53
    livejournal
    -1.51
    ┠
    -1.51
    禵
    -1.50
    bandcamp
    -1.48
    POSITIVE LOGITS
    ter
    1.84
    or
    1.77
    en
    1.71
    no
    1.69
    o
    1.62
    ed
    1.54
    of
    1.53
    k
    1.53
    re
    1.52
    érieurs
    1.51
    Activations Density 0.010%

    No Known Activations