© 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. 24942
    Prev
    Next
    INDEX
    Explanations

    code execution and specific entities

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

    The neuron is triggered by numeric tokens (literal numbers) in code.

    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
     new
    -1.05
     localObject
    -1.00
    putExtra
    -0.99
    ForTesting
    -0.98
     "'";
    -0.96
    čeno
    -0.94
    createCanvas
    -0.93
    reportWebVitals
    -0.92
     paramInt
    -0.92
     with
    -0.89
    POSITIVE LOGITS
    URNS
    1.08
    ệu
    0.99
     マウス
    0.97
    おはよう
    0.97
    uscht
    0.96
    蠵
    0.95
     メニュー
    0.95
     ブロック
    0.94
    ureusement
    0.94
     simil
    0.93
    Activations Density 0.005%

    No Known Activations