© 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. 15612
    Prev
    Next
    INDEX
    Explanations

    actions after "to"

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

    The neuron is a “to” detector—it fires strongly on the token “to,” especially when it introduces an infinitive or direction.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     you
    -1.84
     not
    -1.78
     this
    -1.77
     keep
    -1.73
     by
    -1.73
     on
    -1.73
     which
    -1.72
    {
    -1.69
     your
    -1.66
     some
    -1.66
    POSITIVE LOGITS
     sowieso
    1.54
    یتی
    1.52
     qualif
    1.51
     mengumumkan
    1.51
    Доставка
    1.48
     staffel
    1.48
    niers
    1.46
    пах
    1.45
     verbind
    1.42
     apparaissent
    1.42
    Activations Density 0.044%

    No Known Activations