© 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. 16553
    Prev
    Next
    INDEX
    Explanations

    object a

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

    The neuron primarily detects numeric literals.

    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
     my
    -1.31
     all
    -0.96
     because
    -0.95
    ");
    -0.94
     Did
    -0.93
     every
    -0.92
     check
    -0.91
     what
    -0.90
     logger
    -0.90
    isku
    -0.90
    POSITIVE LOGITS
    ファイルを
    1.13
    Parfait
    1.13
    Idio
    1.00
    Sø
    1.00
     assi
    1.00
     همسر
    0.99
    ODM
    0.98
    Torna
    0.97
     間取り
    0.96
    Dipl
    0.96
    Activations Density 0.000%

    No Known Activations