© 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. 56793
    Prev
    Next
    INDEX
    Explanations

    license software or URLs

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

    The neuron fires on tokens composed of digits (i.e. any numeric token, such as years, counts, version numbers, etc.).

    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
     performance
    -0.76
    SMR
    -0.69
     teren
    -0.69
     Viper
    -0.66
     fasilitas
    -0.64
    spr
    -0.63
     services
    -0.63
    ucci
    -0.62
    benzo
    -0.62
    Approval
    -0.61
    POSITIVE LOGITS
    ZB
    0.70
    namt
    0.69
     Plaza
    0.69
    лаг
    0.68
     Buffet
    0.67
    URL
    0.65
    看得
    0.65
    🛁
    0.65
    wari
    0.64
     заказа
    0.64
    Activations Density 0.121%

    No Known Activations