© 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. 32852
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially programming

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

    The neuron fires on numeric literals (i.e. tokens consisting of digits).

    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
     already
    -1.07
    Viitteet
    -1.01
     weihnachten
    -0.89
     pomaga
    -0.84
    encontra
    -0.81
    Vain
    -0.80
    翆
    -0.79
     lower
    -0.79
    jercicio
    -0.77
     cấu
    -0.77
    POSITIVE LOGITS
    illaries
    0.86
     indigestion
    0.86
     Zinn
    0.85
     '/':
    0.84
     bahkan
    0.84
     even
    0.83
    éré
    0.82
     nuit
    0.82
     Sava
    0.82
     Kammer
    0.81
    Activations Density 0.002%

    No Known Activations