© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72334
    Prev
    Next
    INDEX
    Explanations

    indefinite article 'a' followed by a noun

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

    The neuron activates primarily on numeric tokens (both integers and decimals).

    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
     these
    -1.86
     not
    -1.77
     because
    -1.76
    这些
    -1.71
     are
    -1.67
     when
    -1.65
     there
    -1.64
     so
    -1.63
     with
    -1.62
    歳の
    -1.62
    POSITIVE LOGITS
     Fälle
    1.70
    </strong>
    1.69
     emphasis
    1.59
    锉
    1.56
     elegantly
    1.49
     dalších
    1.49
     quente
    1.45
    身后的
    1.42
     elegante
    1.42
     และ
    1.42
    Activations Density 0.045%

    No Known Activations