© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93593
    Prev
    Next
    INDEX
    Explanations

    default application

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

    The neuron fires on tokens that are numeric literals or contain digits.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     occasion
    -0.81
    Salir
    -0.75
    Comentários
    -0.74
     Occasionally
    -0.73
    近い
    -0.73
    当たり
    -0.71
     něk
    -0.70
     miljoen
    -0.70
     Sometimes
    -0.69
    NSYLVANIA
    -0.69
    POSITIVE LOGITS
    default
    1.96
     default
    1.88
    DEFAULT
    1.77
     Default
    1.70
    Default
    1.57
    默认
    1.28
     DEFAULT
    1.20
    MAIN
    1.14
     main
    1.13
     my
    1.04
    Activations Density 0.277%

    No Known Activations