© 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. 98833
    Prev
    Next
    INDEX
    Explanations

    used to indicate purpose

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

    The neuron detects instances of the “used to …” construction that signal something is being employed for a purpose.

    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
    wrights
    -1.54
    ogues
    -1.54
    eight
    -1.36
     CELLS
    -1.35
    \_
    -1.35
    tling
    -1.34
    ४
    -1.34
     использование
    -1.34
    taya
    -1.33
    ского
    -1.32
    POSITIVE LOGITS
     which
    1.60
     Since
    1.52
     Perhaps
    1.52
     others
    1.51
    鴻
    1.48
     znalaz
    1.45
     schermata
    1.45
     Maybe
    1.45
     would
    1.42
     Schluß
    1.42
    Activations Density 0.101%

    No Known Activations