© 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. 56841
    Prev
    Next
    INDEX
    Explanations

    appeal from the United States

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

    This neuron selectively activates on numeric literals and other tokens composed primarily of digits (e.g., version numbers, file‐index values, large numeric strings).

    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
     from
    -0.96
     if
    -0.95
     start
    -0.90
     or
    -0.89
    tonode
    -0.86
     should
    -0.84
     lipca
    -0.84
    spyOn
    -0.83
    ERÍA
    -0.81
    Ƿ
    -0.81
    POSITIVE LOGITS
    Stap
    1.03
    受伤
    0.92
    Kiel
    0.87
     opio
    0.86
     gekauft
    0.86
     Internation
    0.85
    Cem
    0.85
    τη
    0.84
    Responsable
    0.84
     hexagonal
    0.84
    Activations Density 0.001%

    No Known Activations