© 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. 39420
    Prev
    Next
    INDEX
    Explanations

    words starting with "A"

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

    The neuron fires on the single-letter indefinite article “a” (in either lowercase or uppercase) when it appears by itself as a token.

    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
     other
    -2.11
     these
    -1.81
     this
    -1.81
     various
    -1.80
     on
    -1.80
     additional
    -1.69
     also
    -1.64
     several
    -1.59
     those
    -1.58
    <bos>
    -1.56
    POSITIVE LOGITS
    %",
    1.70
    ije
    1.68
    %;
    1.64
    為に
    1.64
    %',
    1.63
    }{$\
    1.63
    PropertyChanging
    1.62
    だけではなく
    1.60
    Ive
    1.59
    蓠
    1.59
    Activations Density 0.134%

    No Known Activations