© 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. 72221
    Prev
    Next
    INDEX
    Explanations

    animation and code elements

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

    The neuron is triggered by code tokens related to “animation” (e.g. “animation,” “animate,” etc.).

    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
    2
    -2.22
    any
    -1.96
    ’
    -1.91
    ing
    -1.87
    at
    -1.83
     用意
    -1.72
    开来
    -1.72
    as
    -1.64
    ene
    -1.64
    ver
    -1.61
    POSITIVE LOGITS
     –
    1.68
     chaussures
    1.65
    哙
    1.59
    pielen
    1.58
     favoritas
    1.58
    requestCode
    1.57
    pulos
    1.55
    eſt
    1.55
     Isto
    1.55
     habile
    1.53
    Activations Density 0.019%

    No Known Activations