© 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. 22-GEMMASCOPE-RES-131K
    7. 32566
    Prev
    Next
    INDEX
    Explanations

    following date formatting

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

    The neuron fires on numeric literals (tokens composed of digits) in code or config data.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     rám
    -1.03
    Selanjutnya
    -1.02
    oramic
    -1.02
    Lebih
    -1.01
    Obsah
    -0.95
    uncio
    -0.94
    Secara
    -0.94
    Beberapa
    -0.94
    festa
    -0.92
     któ
    -0.90
    POSITIVE LOGITS
    </i>
    1.01
     mens
    1.00
    👧
    0.96
    elerik
    0.96
     wenn
    0.95
    
    0.93
     frem
    0.93
    ','
    0.92
     aber
    0.91
     and
    0.88
    Activations Density 0.025%

    No Known Activations