© 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. 34-GEMMASCOPE-RES-131K
    7. 47069
    Prev
    Next
    INDEX
    Explanations

    compact use

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

    The neuron fires whenever it encounters the word “compact” (in any capitalization) in the text.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Otras
    -0.89
     asseg
    -0.88
     Descub
    -0.88
    ピッタリ
    -0.86
    のカ
    -0.85
     COLL
    -0.85
     Otros
    -0.84
     cliquer
    -0.84
     exceptional
    -0.83
     Alguns
    -0.83
    POSITIVE LOGITS
     Compact
    1.79
    compact
    1.74
     compact
    1.73
    Compact
    1.64
     gọn
    1.20
     compactness
    1.16
     kompakt
    1.16
    ness
    1.14
     компакт
    1.11
    size
    0.98
    Activations Density 0.018%

    No Known Activations