© 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. 22-GEMMASCOPE-RES-131K
    7. 70857
    Prev
    Next
    INDEX
    Explanations

    capitalizing on victims' misfortune"

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

    The neuron activates on numeric expressions (both integers and decimals, including percentages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     It
    -1.77
     You
    -1.64
     if
    -1.61
     If
    -1.43
     `
    -1.35
    axaca
    -1.32
     battle
    -1.30
    secta
    -1.30
    _{\
    -1.30
     Agrega
    -1.27
    POSITIVE LOGITS
     the
    2.78
    蔟
    1.63
     lanterna
    1.55
     sappi
    1.45
     剧照
    1.42
     douleurs
    1.41
     soste
    1.41
     entusias
    1.39
     birra
    1.39
     costumi
    1.36
    Activations Density 0.076%

    No Known Activations