© 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. 59014
    Prev
    Next
    INDEX
    Explanations

    data types and conversions

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

    The neuron detects union indicators—namely occurrences of “or” in text or the vertical‐bar “|” in type declarations.

    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
    isString
    -1.23
    StringProperty
    -1.23
    字符串
    -1.20
     StringField
    -1.15
     STRING
    -1.10
    WriteString
    -1.08
    StringField
    -1.07
    stringValue
    -1.05
    StringLiteral
    -1.05
    弦
    -1.02
    POSITIVE LOGITS
     numerical
    1.07
     numbers
    1.07
     integer
    0.96
     numeric
    0.93
    math
    0.89
     math
    0.87
     other
    0.86
     number
    0.85
     число
    0.80
     números
    0.77
    Activations Density 0.038%

    No Known Activations