© 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. 98924
    Prev
    Next
    INDEX
    Explanations

    stuck or saddled with

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

    The neuron fires on past-participial verbs expressing being burdened or trapped with something (e.g. “lumped with,” “stuck with”).

    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
    𝐞
    -1.59
    </em>
    -1.45
    ématique
    -1.34
     decoradas
    -1.34
     its
    -1.34
     iglesia
    -1.28
     marcadas
    -1.27
    薗
    -1.27
     began
    -1.24
     Iglesia
    -1.24
    POSITIVE LOGITS
     riguard
    1.44
     ricord
    1.38
    𝔶
    1.37
     sogni
    1.36
     calore
    1.36
     ricordo
    1.34
     riguardo
    1.34
    驁
    1.30
     to
    1.30
     particolarmente
    1.30
    Activations Density 0.032%

    No Known Activations