© 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. 104886
    Prev
    Next
    INDEX
    Explanations

    two followed by a hyphen

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

    This neuron detects numeric prefixes joined by a hyphen (e.g. “two-”, “three-”) in technical compound terms like “two-dimensional” or “three-dimensional.”

    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
    ↵
    -1.97
    [
    -1.68
    :
    -1.67
     to
    -1.58
     など
    -1.58
     in
    -1.54
    0
    -1.52
    {
    -1.43
    de
    -1.38
    to
    -1.36
    POSITIVE LOGITS
     alça
    1.50
    聃
    1.49
     вышла
    1.48
    釤
    1.48
    捽
    1.47
     alimento
    1.47
    獃
    1.45
     marcadores
    1.44
     devenir
    1.42
    ூர்
    1.42
    Activations Density 0.073%

    No Known Activations