© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84349
    Prev
    Next
    INDEX
    Explanations

    determiners and pronouns

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

    The neuron strongly activates on very common short function words—especially the definite article “the” (and to a lesser extent pronouns like “it” and auxiliary “is”).

    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
    me
    -1.67
     además
    -1.60
    м
    -1.59
    чен
    -1.58
     Moreover
    -1.58
     aunque
    -1.56
    虽然
    -1.55
     either
    -1.55
    <td>
    -1.51
    ть
    -1.50
    POSITIVE LOGITS
    1
    1.94
     it
    1.82
    2
    1.79
    ごちそう
    1.76
    鳚
    1.73
    3
    1.66
     onderstaande
    1.66
    6
    1.65
     that
    1.63
    名叫
    1.63
    Activations Density 0.038%

    No Known Activations