© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92022
    Prev
    Next
    INDEX
    Explanations

    code and technical contexts

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

    This neuron activates on the vertical‐bar character “|” used as a table or grid delimiter.

    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
     like
    -0.86
     добы
    -0.82
     tertiary
    -0.81
     this
    -0.77
    veni
    -0.76
     microfiber
    -0.75
    涣
    -0.75
    řeba
    -0.75
    тябрь
    -0.75
    issory
    -0.74
    POSITIVE LOGITS
    CYP
    0.81
    BufferedReader
    0.80
    ontale
    0.78
    exporter
    0.77
     позволяют
    0.75
     précédemment
    0.75
     proposent
    0.75
    ではなく
    0.73
     seinem
    0.73
    rune
    0.71
    Activations Density 0.002%

    No Known Activations