© 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. 104390
    Prev
    Next
    INDEX
    Explanations

    code snippets

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

    The neuron fires on occurrences of the phrase “to json” (i.e. calls or definitions of a toJSON serialization method).

    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
    取る
    -0.98
    PostId
    -0.98
    íny
    -0.95
    portun
    -0.93
    MenuList
    -0.93
    reiches
    -0.93
    menuStrip
    -0.92
     ţ
    -0.91
    OrderDetail
    -0.91
    canes
    -0.88
    POSITIVE LOGITS
     -
    0.98
    )$.
    0.93
    ̉
    0.90
    
    0.90
    канчи
    0.89
    :"",
    0.84
     convain
    0.83
    kt
    0.82
     also
    0.82
    BS
    0.81
    Activations Density 0.059%

    No Known Activations