© 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. 75176
    Prev
    Next
    INDEX
    Explanations

    wide range or variety

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

    The neuron fires on the adjective “wide,” particularly when it appears in phrases like “wide range.”

    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
     a
    -2.22
    ”—
    -2.20
     Öffnen
    -1.84
    岨
    -1.76
    .’”
    -1.74
     by
    -1.73
    —”
    -1.72
    ”…
    -1.71
     to
    -1.70
     one
    -1.66
    POSITIVE LOGITS
     -
    2.03
     potrebné
    2.02
    t
    1.96
     kroppen
    1.92
    AutoresizingMask
    1.88
     kampen
    1.86
     programmet
    1.84
    Tidak
    1.84
     réessayer
    1.80
     boissons
    1.76
    Activations Density 0.012%

    No Known Activations