© 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. 58283
    Prev
    Next
    INDEX
    Explanations

    the word panel

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

    The neuron activates on occurrences of the word “panel” (and its compounds or variations, e.g. “display panel,” “cover panel,” “panel discussion,” etc.).

    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
    .
    -2.44
    逦
    -1.88
     Universidades
    -1.84
     receive
    -1.84
    layın
    -1.76
     define
    -1.74
     However
    -1.72
    ↵↵
    -1.72
    Спасылкі
    -1.70
     Recommended
    -1.69
    POSITIVE LOGITS
     ними
    2.11
    是非常
    2.05
     specialising
    1.98
    事を
    1.94
    ⽥
    1.91
    遹
    1.91
    岜
    1.90
    ndash
    1.90
    .'
    1.88
     cites
    1.88
    Activations Density 0.018%

    No Known Activations