© 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. 72943
    Prev
    Next
    INDEX
    Explanations

    quite a lot

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

    This neuron specifically detects the indefinite article “a” when it’s part of the intensifier phrase “quite a.”

    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
    に
    -2.13
    ৢ
    -2.06
     to
    -2.06
    2
    -1.98
     für
    -1.98
    いちご
    -1.93
     anunciou
    -1.93
    淠
    -1.91
     pursuant
    -1.91
     notwendig
    -1.90
    POSITIVE LOGITS
    人都
    2.08
     promove
    1.99
     crap
    1.98
    +}$
    1.96
     rubbish
    1.91
     dread
    1.87
    饜
    1.86
    前方
    1.84
    亮的
    1.84
    LLABLE
    1.83
    Activations Density 0.002%

    No Known Activations