© 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. 85463
    Prev
    Next
    INDEX
    Explanations

    want to + verb

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

    The neuron fires on bare infinitive verb constructions—especially the “to” + verb pattern.

    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
    Even
    -1.32
     incluso
    -1.31
    even
    -1.28
     nawet
    -1.27
     даже
    -1.27
     even
    -1.16
     навіть
    -1.14
     möjlighet
    -1.12
     тебя
    -1.09
     حتی
    -1.09
    POSITIVE LOGITS
     of
    1.75
     about
    1.37
     ufficio
    1.20
     such
    1.17
     comprensión
    1.16
     Для
    1.15
     must
    1.13
    alamy
    1.13
     artikke
    1.12
    ėjimas
    1.12
    Activations Density 0.309%

    No Known Activations