© 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. 45430
    Prev
    Next
    INDEX
    Explanations

    animation in code and libraries

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

    The neuron fires on occurrences of the word “animate” (and its variants like “animation,” “animating,” etc.), i.e. references to animate‐related function calls or terms.

    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
    。
    -2.69
     Näch
    -2.53
    ’
    -2.52
    ра
    -2.41
    」
    -2.38
     .
    -2.31
     alcuni
    -2.27
    2
    -2.27
     \
    -2.20
     \'
    -2.20
    POSITIVE LOGITS
     unrelenting
    3.09
    ?”
    2.78
     supremely
    2.70
    -”
    2.56
    -
    2.45
    笮
    2.44
     erratic
    2.42
     invigor
    2.39
     unwavering
    2.38
     rejuven
    2.34
    Activations Density 0.001%

    No Known Activations