© 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. 64620
    Prev
    Next
    INDEX
    Explanations

    programming syntax and parameters

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

    The neuron strongly activates on numeric tokens (e.g. integers, floats, version numbers, parameter values) in code or documentation.

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

    No Comments

    Negative Logits
    śli
    -1.02
    шение
    -0.95
     Comte
    -0.90
     устройств
    -0.89
    ⒈
    -0.89
     elección
    -0.88
     keuze
    -0.88
     Drapeau
    -0.88
     seleccionados
    -0.87
    redning
    -0.86
    POSITIVE LOGITS
    tabular
    0.98
     Tourismus
    0.90
     mewakili
    0.88
     búsquedas
    0.85
     conversaciones
    0.83
     energías
    0.82
     type
    0.81
    似乎
    0.81
     situato
    0.81
     produces
    0.80
    Activations Density 0.031%

    No Known Activations