© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69004
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

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

    The neuron detects numeric data values—especially decimal or percentage figures—in statistical contexts.

    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
    if
    -1.77
    その
    -1.63
    to
    -1.62
    ”
    -1.56
    さらに
    -1.52
    il
    -1.45
     to
    -1.42
    所
    -1.42
    the
    -1.40
     ”
    -1.39
    POSITIVE LOGITS
     themselves
    1.80
    dáms
    1.79
     there
    1.72
    mereka
    1.70
     from
    1.65
    artisan
    1.60
     they
    1.59
    Mereka
    1.57
    businessman
    1.55
     hvě
    1.55
    Activations Density 0.129%

    No Known Activations