© 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-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10830
    Prev
    Next
    INDEX
    Explanations

    specific code examples

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

    The neuron strongly activates on programming identifiers or tool commands (e.g. function names and command‐line utilities).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     user
    1.08
     data
    1.05
     =
    1.02
     runtime
    1.01
    调用
    0.98
     unicode
    0.96
     filesystem
    0.96
     initialization
    0.94
     <=
    0.94
     namespace
    0.93
    POSITIVE LOGITS
     निजामाच्या
    1.02
     इंग्लंड
    0.99
     आरमारा
    0.99
     लष्
    0.98
     आरमार
    0.98
     पुण्या
    0.97
     जलाश
    0.96
     प्रश्‍
    0.96
     पंतप्रधान
    0.96
    ेंद्रीय
    0.95
    Activations Density 0.000%

    No Known Activations