© 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. 106349
    Prev
    Next
    INDEX
    Explanations

    created by

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

    The neuron fires primarily on numeric date tokens (years, months, days) and their separator slashes in file header comments.

    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
     calificaciones
    -0.75
     tercio
    -0.74
    processData
    -0.74
     미국
    -0.73
     Сме
    -0.73
     Leon
    -0.73
    TargetApi
    -0.72
    흥
    -0.71
     Issue
    -0.71
    irements
    -0.71
    POSITIVE LOGITS
    ☆☆☆☆
    0.87
    URATION
    0.81
     Municip
    0.80
     rosse
    0.80
     Portugu
    0.79
     piet
    0.78
     YET
    0.78
     Retrieval
    0.76
     Salva
    0.75
     marqués
    0.74
    Activations Density 0.019%

    No Known Activations