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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59733
    Prev
    Next
    INDEX
    Explanations

    InfluxDB, Grafana, Kibana

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

    The neuron primarily activates on numerical tokens (digits, version numbers, or numeric literals).

    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
    দ্
    -0.77
    ICKEN
    -0.71
    castle
    -0.71
    platin
    -0.70
    coff
    -0.70
    Crawl
    -0.70
     Forscher
    -0.69
     withdrawn
    -0.68
     пальто
    -0.68
     roadmap
    -0.67
    POSITIVE LOGITS
     Graf
    1.68
     influx
    1.36
    Graf
    1.33
     graf
    1.23
    graf
    1.23
     Influ
    1.16
     Graphite
    1.08
    Influ
    1.04
     Kib
    1.00
    ograf
    0.99
    Activations Density 0.091%

    No Known Activations