© 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. 22-GEMMASCOPE-RES-131K
    4. 39336
    Prev
    Next
    INDEX
    Explanations

    sets followed by semicolon

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

    This neuron activates on the “set” accessor in property definitions (i.e., occurrences of “set” in code).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     and
    -1.56
     it
    -1.45
     by
    -1.44
     their
    -1.38
    眼下
    -1.34
     to
    -1.32
     a
    -1.28
     which
    -1.21
     where
    -1.17
     almost
    -1.15
    POSITIVE LOGITS
    <bos>
    1.45
    6
    1.36
    もありました
    1.34
    Descriere
    1.32
    もありますが
    1.30
    もあります
    1.20
    Président
    1.18
    3
    1.18
    もあって
    1.18
     heridos
    1.16
    Activations Density 0.000%

    No Known Activations