© 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. 30138
    Prev
    Next
    INDEX
    Explanations

    abbreviations and initialisms

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

    The neuron fires on long numeric literals (multi-digit numbers) in the 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
     Yet
    -1.17
     definite
    -1.02
     definitive
    -0.95
     Констан
    -0.94
    iap
    -0.91
     daze
    -0.91
     yet
    -0.91
     olduğ
    -0.90
    ibouti
    -0.88
     worst
    -0.87
    POSITIVE LOGITS
     marie
    0.91
     archi
    0.90
    场的
    0.90
    zauber
    0.89
     otel
    0.89
     vell
    0.88
     ervaring
    0.88
     gamin
    0.87
     poisson
    0.85
     vert
    0.84
    Activations Density 0.440%

    No Known Activations