© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73037
    Prev
    Next
    INDEX
    Explanations

    "get", "add", "update", "read", "set", "connect"

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

    This neuron responds to occurrences of “get” (or “get”-prefixed) identifiers in code, especially variable and function names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    llllll
    -1.69
    YYY
    -1.62
    romeda
    -1.50
     adolescente
    -1.45
    ***/
    -1.43
     politika
    -1.39
    farer
    -1.38
    蕺
    -1.36
    >"+
    -1.36
    EEEE
    -1.35
    POSITIVE LOGITS
     Some
    1.60
     them
    1.55
     from
    1.55
     Many
    1.48
    It
    1.45
     February
    1.44
     which
    1.41
     Maybe
    1.36
     stated
    1.36
    '
    1.35
    Activations Density 0.087%

    No Known Activations