© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86050
    Prev
    Next
    INDEX
    Explanations

    With the + state of affairs

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

    The neuron consistently activates on the definite article “the.”

    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
     what
    -2.63
     should
    -2.25
     and
    -2.17
     when
    -2.17
     but
    -2.06
     why
    -1.68
     those
    -1.68
     would
    -1.68
    8
    -1.67
    on
    -1.66
    POSITIVE LOGITS
     sintomas
    1.53
    ︲
    1.52
    ю
    1.48
    ໊
    1.47
     of
    1.47
     suffisamment
    1.45
    Their
    1.45
    akte
    1.42
     betek
    1.41
     habile
    1.39
    Activations Density 0.013%

    No Known Activations