© 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. 10-GEMMASCOPE-RES-131K
    7. 13453
    Prev
    Next
    INDEX
    Explanations

    keys and values separated by colons

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

    This neuron detects parameter names in code (i.e. identifiers used as keys in key–value or keyword arguments such as “from”, “to”, “on”, etc.).

    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
    gud
    -1.60
    noah
    -1.49
     antecedentes
    -1.43
    buon
    -1.41
    tadr
    -1.41
     fashioned
    -1.41
    thail
    -1.41
    只是一个
    -1.40
     guidance
    -1.39
     valioso
    -1.39
    POSITIVE LOGITS
    mathrm
    1.95
     \
    1.73
     که
    1.70
    e
    1.63
    \
    1.61
     "
    1.52
     которое
    1.47
    TestingModule
    1.46
     је
    1.45
    Si
    1.42
    Activations Density 0.006%

    No Known Activations