© 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. 30022
    Prev
    Next
    INDEX
    Explanations

    compression file extensions

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

    This neuron detects numeric literals—especially multi-digit numbers—in code or 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
    zers
    -0.80
     setImage
    -0.75
     rud
    -0.72
     alike
    -0.69
     ради
    -0.68
     revealed
    -0.68
    灝
    -0.67
    watt
    -0.66
     CAV
    -0.65
    Hew
    -0.65
    POSITIVE LOGITS
     compressed
    2.14
     compression
    1.94
    压缩
    1.76
    compressed
    1.74
     gzip
    1.67
     compress
    1.65
    Compressed
    1.64
    Compression
    1.61
    gz
    1.59
     Compressed
    1.56
    Activations Density 0.042%

    No Known Activations